© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12412
    Prev
    Next
    INDEX
    Explanations

    scoring, goals, or stats

    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
     varones
    -1.13
    êt
    -1.09
     +/-
    -1.09
     Процитовано
    -1.07
     quando
    -1.07
    扱う
    -1.06
     Offisielt
    -1.05
    龙头
    -1.05
    MenuInflater
    -1.04
    MultipartFile
    -1.03
    POSITIVE LOGITS
     ativar
    1.02
     オブ
    1.00
    Kdo
    0.94
    嗒
    0.94
    Fak
    0.91
     хотят
    0.89
     desactivar
    0.88
     joie
    0.87
     tropic
    0.87
     itſelf
    0.86
    Activations Density 0.028%

    No Known Activations