© 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. 79096
    Prev
    Next
    INDEX
    Explanations

    Al- names or prefixes

    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
    を
    -0.97
    があります
    -0.94
    などを
    -0.92
    hlás
    -0.91
    などが
    -0.89
     algas
    -0.89
    それも
    -0.87
     diinginkan
    -0.85
    餃子
    -0.84
     школа
    -0.83
    POSITIVE LOGITS
    有一
    1.09
    為に
    1.02
     dessa
    1.01
    écri
    1.01
     culoare
    0.98
    essayer
    0.97
    appliquer
    0.96
    Feel
    0.95
    KO
    0.94
    icoot
    0.93
    Activations Density 0.012%

    No Known Activations