© 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. 83017
    Prev
    Next
    INDEX
    Explanations

    FIR registration

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

    side effects, immediate area

    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
    <0x82>
    0.50
    uity
    0.48
     że
    0.46
     RTI
    0.46
     malice
    0.44
    りで
    0.43
    ēr
    0.43
     impunity
    0.43
    ன
    0.42
     tradeoffs
    0.42
    POSITIVE LOGITS
    と同様
    0.45
    reversible
    0.44
    FormParams
    0.44
    llllll
    0.42
    នុស្ស
    0.42
    苳
    0.42
     stále
    0.41
    ColorBit
    0.41
     灬
    0.41
    ..
    0.41
    Activations Density 0.000%

    No Known Activations