© 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. 58619
    Prev
    Next
    INDEX
    Explanations

    depends on

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

    depends on

    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
     are
    0.60
    s
    0.59
    to
    0.48
     classify
    0.48
     olhos
    0.48
    i
    0.46
    ka
    0.46
     generate
    0.45
    bowtie
    0.45
    f
    0.45
    POSITIVE LOGITS
     달라
    0.52
     Climate
    0.51
     Qualifications
    0.50
    मात्र
    0.49
    <unused43>
    0.49
     banget
    0.49
    लया
    0.48
    ścic
    0.48
    ৩
    0.48
    เวอร์
    0.48
    Activations Density 0.008%

    No Known Activations