© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72237
    Prev
    Next
    INDEX
    Explanations

    legal citations or numbers

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

    The neuron flags standalone numeric tokens—i.e. sequences of digits representing measurements, identifiers, or other numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    諼
    -2.20
     (!__
    -2.13
    でご
    -2.13
     desmotiv
    -2.06
     sentarse
    -2.02
     reír
    -2.02
     a
    -1.97
     rheinland
    -1.96
    corrhi
    -1.96
    に行った
    -1.95
    POSITIVE LOGITS
    は
    2.25
    がありますが
    2.16
    などが
    2.14
    を
    2.03
    <bos>
    2.03
    r
    1.96
    も
    1.95
    m
    1.95
    もあります
    1.89
     –
    1.88
    Activations Density 0.059%

    No Known Activations