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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12220
    Prev
    Next
    INDEX
    Explanations

    quantities and specific nouns

    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
     which
    -1.11
    klá
    -1.09
     لهذا
    -1.08
    ônica
    -1.05
     that
    -1.05
     $=$
    -1.05
     especially
    -1.05
    𝒒
    -1.04
    owania
    -1.01
    ků
    -1.00
    POSITIVE LOGITS
     NSCoder
    1.13
     sepen
    1.05
     offrir
    1.05
    伟大
    1.04
    Beskrivelse
    1.04
    tualmente
    1.04
    electro
    1.03
     basse
    1.01
     gratuite
    1.01
     gioia
    1.00
    Activations Density 0.073%

    No Known Activations