© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129797
    Prev
    Next
    INDEX
    Explanations

    call sign and fm/am suffixes

    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
     specific
    -1.40
     support
    -1.39
    ？！”
    -1.38
     during
    -1.32
     about
    -1.27
     their
    -1.25
     nuevas
    -1.23
     even
    -1.20
     specially
    -1.20
     work
    -1.17
    POSITIVE LOGITS
     Septembre
    1.61
     monstre
    1.59
     maksi
    1.59
     nini
    1.51
     DANCE
    1.51
    🍗
    1.49
     Octobre
    1.48
     RADIO
    1.47
     LUNCH
    1.46
     harap
    1.45
    Activations Density 0.076%

    No Known Activations