© 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. 65169
    Prev
    Next
    INDEX
    Explanations

    anchor

    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
    慥
    -2.08
    苤
    -2.06
    ارتمان
    -2.06
    ’
    -2.02
    々な
    -1.98
     hotelu
    -1.98
     But
    -1.98
     enough
    -1.98
     來
    -1.97
    鶫
    -1.95
    POSITIVE LOGITS
    沇
    2.50
    ೢ
    2.19
    ྜ
    2.19
    h
    2.09
    </b>
    2.09
    }$,
    2.06
    ଃ
    2.06
    Ꮉ
    2.05
    ")]
    2.02
     steadfast
    2.02
    Activations Density 0.007%

    No Known Activations