© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101063
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or braces

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "string" when used as a type declaration in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of identifiers declared with the “string” type in code (e.g. function parameters or variables of type string).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    []>(
    -2.06
    )),
    -2.06
     веке
    -1.91
     kartą
    -1.82
    文化的
    -1.81
    ),),
    -1.81
    社会的
    -1.77
    providedIn
    -1.77
     厂家
    -1.74
    ).
    -1.73
    POSITIVE LOGITS
    0
    2.55
    3
    2.53
    6
    2.33
    8
    2.19
    9
    2.17
    7
    2.14
    1
    1.97
    4
    1.96
    5
    1.95
    2
    1.92
    Activations Density 0.008%

    No Known Activations