© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118747
    Prev
    Next
    INDEX
    Explanations

    describing methods

    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
     potra
    -1.05
    ură
    -1.00
    Which
    -0.98
    χρι
    -0.94
    dä
    -0.94
    がいい
    -0.93
    €“
    -0.92
    kunden
    -0.92
    formik
    -0.90
    PROLOG
    -0.90
    POSITIVE LOGITS
     that
    1.55
     of
    1.31
     is
    0.97
     như
    0.94
     like
    0.93
     during
    0.90
     such
    0.90
     there
    0.88
    ,,
    0.85
     oneself
    0.85
    Activations Density 0.046%

    No Known Activations