© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65023
    Prev
    Next
    INDEX
    Explanations

    method calls accessing data

    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_22/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
     firft
    -1.10
     vernac
    -1.08
    ğlık
    -1.05
    DÉ
    -1.05
     mercen
    -1.04
     publice
    -1.04
     Juden
    -1.02
     situe
    -1.02
     ananas
    -1.02
     artig
    -1.01
    POSITIVE LOGITS
     from
    1.82
     through
    1.23
     During
    1.22
     any
    1.16
     during
    1.11
     Any
    1.07
    至此
    1.05
    During
    1.03
     if
    1.02
    TintMode
    0.99
    Activations Density 0.004%

    No Known Activations