© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30087
    Prev
    Next
    INDEX
    Explanations

    door entry, Eezi rigs, It Ain't Safe

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

    The neuron fires on numeric tokens, i.e. sequences of digits representing numbers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Entries
    -0.78
    isiä
    -0.77
     memanfaatkan
    -0.77
    攒
    -0.77
     Schi
    -0.75
     sveta
    -0.74
    arası
    -0.73
     Salta
    -0.73
     Crot
    -0.73
     Audits
    -0.69
    POSITIVE LOGITS
     carp
    1.20
     banks
    0.94
     biv
    0.94
     Carp
    0.94
     PVA
    0.92
     alarms
    0.90
    Carp
    0.89
     bank
    0.88
     crayfish
    0.88
     baits
    0.86
    Activations Density 0.005%

    No Known Activations