© 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. 10-GEMMASCOPE-RES-131K
    7. 99445
    Prev
    Next
    INDEX
    Explanations

    specific words

    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
    S
    -2.89
    C
    -2.84
     небольшой
    -2.64
    ሷ
    -2.53
    <bos>
    -2.52
    ],
    -2.39
     "]";
    -2.38
    军的
    -2.34
    。】
    -2.31
    珰
    -2.31
    POSITIVE LOGITS
    緇
    3.28
    琹
    2.88
    盌
    2.84
    饧
    2.81
    퐸
    2.80
    푎
    2.75
    ࿙
    2.63
    媖
    2.58
     disbursed
    2.55
    ющие
    2.52
    Activations Density 0.001%

    No Known Activations