© 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. 10033
    Prev
    Next
    INDEX
    Explanations

    variation

    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
     Reſ
    -2.44
    ㈮
    -2.33
    覿
    -2.30
     Inſ
    -2.22
     Ukraina
    -2.17
     citroen
    -2.14
    踯
    -2.14
    踽
    -2.13
     Diſ
    -2.11
    夘
    -2.11
    POSITIVE LOGITS
    </h3>
    2.56
    and
    2.41
     $
    2.38
     the
    2.19
     и
    2.05
     ihre
    2.00
     και
    1.99
    .
    1.91
     gärna
    1.88
     at
    1.84
    Activations Density 0.043%

    No Known Activations