© 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. 100274
    Prev
    Next
    INDEX
    Explanations

    choose a new

    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
    และ
    -2.31
    ꔛ
    -2.28
    艽
    -2.28
    ⚣
    -2.19
    𖡼
    -2.14
    した
    -2.13
    ㋛
    -2.08
    渽
    -2.05
     lettura
    -2.02
     empfiehlt
    -1.98
    POSITIVE LOGITS
    able
    2.48
    have
    2.27
     However
    2.27
    Mereka
    2.05
     BOTH
    2.00
    뚤
    1.92
    after
    1.91
     multitude
    1.89
     Then
    1.89
    </strong>
    1.89
    Activations Density 0.005%

    No Known Activations