© 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. 44366
    Prev
    Next
    INDEX
    Explanations

    Ustaša

    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
    A
    -2.80
    ol
    -2.75
    D
    -2.70
    Y
    -2.47
    to
    -2.41
    -2.39
    e
    -2.34
    这个
    -2.34
    ag
    -2.33
    9
    -2.31
    POSITIVE LOGITS
    糶
    2.39
    ⎚
    2.34
     necesar
    2.22
     and
    2.20
     relation
    2.06
    INOIS
    2.02
     modifica
    2.02
     fiind
    2.02
     produse
    2.00
     subje
    2.00
    Activations Density 0.000%

    No Known Activations