© 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. 55677
    Prev
    Next
    INDEX
    Explanations

    C type casting

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

    float assignment

    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
     arrows
    0.47
     instruction
    0.43
    ())->
    0.42
    instructions
    0.41
     Sterne
    0.41
     instructions
    0.41
    <0x96>
    0.41
    hah
    0.41
    잍
    0.41
    Ѡ
    0.40
    POSITIVE LOGITS
     پیم
    0.50
     puncak
    0.45
    чений
    0.44
     झेल
    0.44
     Bewohner
    0.43
    rystals
    0.42
     `<=
    0.42
    渕
    0.42
     உட்ப
    0.41
    دهای
    0.41
    Activations Density 0.000%

    No Known Activations