© 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. 34-GEMMASCOPE-RES-131K
    7. 30594
    Prev
    Next
    INDEX
    Explanations

    Git branch, Gson, comment group

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

    This neuron detects long numeric (and alphanumeric) sequences used as software version numbers or cryptographic hashes.

    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
    lehem
    -0.76
    attro
    -0.74
     Calab
    -0.72
    ">{{
    -0.72
     Callahan
    -0.72
    竞技
    -0.71
     במה
    -0.70
    SYSTEM
    -0.68
    خی
    -0.67
     MANUAL
    -0.67
    POSITIVE LOGITS
    creds
    0.65
     owl
    0.65
     Kleidung
    0.64
    ㄱ
    0.62
    owl
    0.62
     nitrogen
    0.62
    聲音
    0.60
    🤒
    0.60
    mrc
    0.60
     verifier
    0.59
    Activations Density 0.036%

    No Known Activations