© 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. 38970
    Prev
    Next
    INDEX
    Explanations

    at this point

    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
    </i>
    -2.02
    </h2>
    -1.96
    </td>
    -1.82
     when
    -1.71
    </em>
    -1.57
    </blockquote>
    -1.47
     still
    -1.41
    代わり
    -1.38
     dennoch
    -1.38
     section
    -1.38
    POSITIVE LOGITS
    стреча
    1.52
     mette
    1.52
     différente
    1.47
     手绘
    1.44
    螃
    1.42
     corrom
    1.41
    yship
    1.40
    juego
    1.39
    lihood
    1.38
    新しい
    1.38
    Activations Density 0.013%

    No Known Activations