© 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. 59359
    Prev
    Next
    INDEX
    Explanations

    chart, usage, annual, difficulties, average

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

    improvement and instability

    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
     資
    0.44
    ）。
    0.43
    .").
    0.43
     रणनीति
    0.42
    grad
    0.41
     kavram
    0.40
    tres
    0.40
    நாம்
    0.40
    resc
    0.38
    argon
    0.38
    POSITIVE LOGITS
    そのまま
    0.46
    醸
    0.45
     immédi
    0.45
     counts
    0.44
     pillows
    0.43
     প্রত্যক্ষ
    0.43
     inhoud
    0.43
    igt
    0.42
     cyclones
    0.42
     trips
    0.42
    Activations Density 0.000%

    No Known Activations