© 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. 106684
    Prev
    Next
    INDEX
    Explanations

    either expect or rating

    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
     from
    -1.42
     and
    -1.41
     which
    -1.32
    ところに
    -1.32
     with
    -1.21
    予定です
    -1.17
     that
    -1.16
     Drž
    -1.16
    ところは
    -1.16
    ड़ा
    -1.10
    POSITIVE LOGITS
    is
    1.33
    1.20
    in
    1.10
     alguns
    1.10
     aVar
    1.07
    p
    1.06
    ns
    1.05
    tt
    1.05
    rt
    1.02
    pi
    1.02
    Activations Density 0.026%
    No Known Activations