© 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. 106185
    Prev
    Next
    INDEX
    Explanations

    bibliographic references

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     akibat
    -0.83
    amá
    -0.81
    広島
    -0.81
    tione
    -0.80
    ipp
    -0.80
    ⌄
    -0.77
    andri
    -0.77
    Ổ
    -0.76
    тами
    -0.76
    vola
    -0.76
    POSITIVE LOGITS
     Vanessa
    0.68
     oppose
    0.66
    zza
    0.66
     TRAN
    0.66
    hirt
    0.65
    пры
    0.65
    véni
    0.65
     Marina
    0.64
    Fen
    0.63
    CREDIT
    0.63
    Activations Density 0.036%

    No Known Activations