© 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. 22-GEMMASCOPE-RES-131K
    7. 26020
    Prev
    Next
    INDEX
    Explanations

    origin or source

    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
    <bos>
    -1.37
     to
    -1.36
     that
    -1.21
     $
    -1.19
     it
    -1.09
    >
    -1.08
     of
    -1.08
     =
    -1.06
     longtime
    -1.06
     women
    -1.05
    POSITIVE LOGITS
     afar
    1.45
     assise
    1.24
    élaboration
    1.23
    исленность
    1.20
     boîtier
    1.13
    équipement
    1.11
    vät
    1.10
    DebuggerNonUser
    1.10
     łóż
    1.09
    に行ってきました
    1.09
    Activations Density 0.037%

    No Known Activations