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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 95324
    Prev
    Next
    INDEX
    Explanations

    bibliographic citations

    np_acts-logits-general · gemini-2.5-flash-lite

    Check, July, Path, Difficulty, Meter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tryptophan
    0.46
     proteine
    0.43
     hyst
    0.43
     hysteresis
    0.43
     phd
    0.42
     $\
    0.41
     metod
    0.41
    experiments
    0.41
     proteolytic
    0.40
    viously
    0.40
    POSITIVE LOGITS
    就會
    0.47
    ဘာ
    0.46
    थिंग
    0.42
    टेल
    0.41
    <unused1>
    0.41
    leau
    0.40
     الكون
    0.40
     होऊ
    0.40
    倏
    0.40
    ንን
    0.39
    Activations Density 0.000%

    No Known Activations