© 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. 34-GEMMASCOPE-RES-131K
    7. 117538
    Prev
    Next
    INDEX
    Explanations

    Structure and meta-information

    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_34/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
     so
    -1.60
     by
    -1.45
     more
    -1.41
     when
    -1.34
     without
    -1.27
     on
    -1.26
     at
    -1.26
    Although
    -1.25
     unrelenting
    -1.23
     with
    -1.23
    POSITIVE LOGITS
     almohada
    1.42
     pensamientos
    1.41
     horrid
    1.34
     delightfully
    1.28
     vijf
    1.28
     deliciously
    1.27
     srdce
    1.27
     trám
    1.26
     revamped
    1.25
    に入れる
    1.25
    Activations Density 0.000%

    No Known Activations