© 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. 87708
    Prev
    Next
    INDEX
    Explanations

    . First, of facts, generally the, visualize the

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

    understanding explanations and consequences

    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
     quadrant
    0.47
     einzigen
    0.46
     handles
    0.46
     法
    0.45
     이유는
    0.45
     entities
    0.45
     О
    0.45
     (),
    0.45
     (){
    0.44
     транспорт
    0.44
    POSITIVE LOGITS
     Sprint
    0.44
    ケート
    0.44
    ப்புகளை
    0.44
     Ngọc
    0.43
     Brawl
    0.43
    in
    0.42
    atud
    0.42
     speck
    0.42
     Rookie
    0.42
    桀
    0.42
    Activations Density 0.000%

    No Known Activations