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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84970
    Prev
    Next
    INDEX
    Explanations

    Milford Rd. and license conditions

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

    The neuron is triggered by tokens denoting numeric version or license identifiers (e.g. multi-digit version numbers and “LICENSE_1_0.txt”-style strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Literal
    -0.81
    Pressed
    -0.74
    Tracer
    -0.69
     Lobby
    -0.66
    Literal
    -0.66
     Pressed
    -0.66
    لاع
    -0.65
     մ
    -0.65
     worthy
    -0.64
    phrag
    -0.64
    POSITIVE LOGITS
     restraint
    0.74
    dds
    0.69
     Format
    0.69
    layout
    0.67
     Carroll
    0.67
    ЕНЬ
    0.65
    Carroll
    0.65
     कभी
    0.64
    processData
    0.63
     Track
    0.63
    Activations Density 0.079%

    No Known Activations