© 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. 11517
    Prev
    Next
    INDEX
    Explanations

    dip, HD, Ch, dop occurrences

    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
    ᜀ
    -1.21
    mbal
    -1.13
     男人
    -1.11
    Pä
    -1.10
     heilig
    -1.10
    äldrar
    -1.09
    nappropriate
    -1.07
    最終
    -1.03
     kostenlose
    -1.03
    mogen
    -1.02
    POSITIVE LOGITS
     there
    1.09
     aforesaid
    1.05
     still
    1.04
    遽
    0.98
     and
    0.98
     hardly
    0.95
    *
    0.95
     even
    0.94
     betrachtet
    0.94
     will
    0.94
    Activations Density 0.061%

    No Known Activations