© 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. 67624
    Prev
    Next
    INDEX
    Explanations

    code identifiers and delimiters

    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
     what
    -1.81
     with
    -1.26
    realme
    -1.21
     according
    -1.20
     where
    -1.18
     who
    -1.17
    collant
    -1.15
     gave
    -1.13
     came
    -1.12
    ixote
    -1.12
    POSITIVE LOGITS
     questa
    1.50
    !
    1.40
    this
    1.38
     questo
    1.38
    \_
    1.36
    ,,,
    1.33
    ㄱ
    1.30
     хорошее
    1.28
     >::
    1.27
    >=
    1.23
    Activations Density 0.159%

    No Known Activations