© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13479
    Prev
    Next
    INDEX
    Explanations

    information

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

    multi-part concepts

    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_16k_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
    आज
    0.44
    cij
    0.44
     acquire
    0.42
     अथ
    0.42
    Giải
    0.40
    vius
    0.40
    츠
    0.40
     danas
    0.38
    航空
    0.38
    러스
    0.38
    POSITIVE LOGITS
     pungent
    0.41
     vibrational
    0.40
     pads
    0.39
     _)
    0.39
     enzymes
    0.38
    indent
    0.38
     enzimas
    0.38
    identifiers
    0.38
    columns
    0.38
    裹
    0.38
    Activations Density 0.000%

    No Known Activations