© 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. 47688
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
     også
    -0.94
     卓
    -0.93
    morgan
    -0.90
    idar
    -0.90
    pleft
    -0.89
     architekt
    -0.85
    emore
    -0.84
    зец
    -0.83
     červen
    -0.82
     arī
    -0.82
    POSITIVE LOGITS
     esist
    0.81
    Finite
    0.79
     Lade
    0.78
    цима
    0.77
     Grü
    0.73
     sinistra
    0.72
    ユ
    0.72
     frightened
    0.72
    anim
    0.72
     Alters
    0.71
    Activations Density 0.000%

    No Known Activations