© 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. 110812
    Prev
    Next
    INDEX
    Explanations

    idle state or commands

    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
    E
    -2.23
     denselben
    -2.14
    曷
    -2.08
     ‘’
    -1.98
     牌
    -1.98
    谖
    -1.98
    and
    -1.97
     hvem
    -1.94
    袛
    -1.91
    </td>
    -1.91
    POSITIVE LOGITS
    }
    2.41
    ?"
    2.39
     For
    2.16
    )
    2.13
    !!"
    2.06
    翾
    2.06
    --
    2.02
    となります
    1.99
    '!
    1.99
    を使う
    1.98
    Activations Density 0.003%

    No Known Activations