© 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. 34-GEMMASCOPE-RES-131K
    7. 102927
    Prev
    Next
    INDEX
    Explanations

    US states

    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_34/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
     profondità
    -1.13
    にします
    -1.12
     either
    -1.12
     like
    -1.11
     of
    -1.09
     próprio
    -1.08
     difficoltà
    -1.06
     Vergnügen
    -1.06
     모두
    -1.02
     şun
    -1.02
    POSITIVE LOGITS
     USA
    1.39
    USA
    1.34
    area
    1.28
     area
    1.13
     where
    1.07
     Gerais
    1.02
    зії
    1.00
    leine
    0.98
     plafon
    0.98
     área
    0.97
    Activations Density 0.081%

    No Known Activations