© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69307
    Prev
    Next
    INDEX
    Explanations

    how to

    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_10/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
     but
    -2.13
     those
    -1.53
     "
    -1.43
     both
    -1.32
     This
    -1.25
    erobic
    -1.23
     beschäf
    -1.22
     machten
    -1.22
    kward
    -1.21
    '")
    -1.20
    POSITIVE LOGITS
     abbraccio
    1.43
     rengi
    1.35
     eseguire
    1.35
     ottimo
    1.34
     ]);
    1.31
     abband
    1.29
     KI
    1.29
     любого
    1.28
     pagare
    1.28
     profumo
    1.27
    Activations Density 0.002%

    No Known Activations