© 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. 15017
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    EdgeInsets
    -1.23
    ﻻ
    -1.20
    pretty
    -1.14
     Tujuan
    -1.11
     aficionados
    -1.05
    研发
    -1.05
     Sollte
    -1.05
    й
    -1.05
    ではなく
    -1.03
    UInt
    -1.02
    POSITIVE LOGITS
     rús
    1.37
     their
    1.21
     want
    1.20
     decorados
    1.17
     pouce
    1.14
     хоте
    1.10
     reformed
    1.08
     pouring
    1.08
     studying
    1.05
     alemania
    1.04
    Activations Density 0.012%

    No Known Activations