© 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. 20797
    Prev
    Next
    INDEX
    Explanations

    callingwithinURLMatthewNepal

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

    describing variations and predictions

    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
    ="<%=
    0.46
     Kershaw
    0.46
     European
    0.45
     "./
    0.45
    éu
    0.43
     Old
    0.43
     Fitness
    0.43
    éra
    0.42
    Everyone
    0.42
    ժ
    0.42
    POSITIVE LOGITS
    제를
    0.45
    ЛИ
    0.44
     సంబంధ
    0.43
    জন্য
    0.41
     propylene
    0.41
    ORGAN
    0.41
    ology
    0.41
    사에
    0.41
    又は
    0.40
    विष
    0.40
    Activations Density 0.003%

    No Known Activations