© 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. 67296
    Prev
    Next
    INDEX
    Explanations

    Builder and Long types

    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
    ers
    -1.48
     giebt
    -1.45
    </em>
    -1.44
    主要是
    -1.31
    に対して
    -1.31
    because
    -1.31
    They
    -1.27
    Skocz
    -1.27
    through
    -1.24
    anguera
    -1.24
    POSITIVE LOGITS
    CONSIN
    1.33
     americanos
    1.24
     plafon
    1.21
     malé
    1.20
     vouloir
    1.20
    Seoul
    1.19
     tableta
    1.18
     renom
    1.16
     so
    1.16
     a
    1.16
    Activations Density 0.017%

    No Known Activations