© 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. 123365
    Prev
    Next
    INDEX
    Explanations

    universal precautions

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

    copyrighted, discovered, divide, cocaine, however

    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
    ड
    0.49
    지의
    0.48
    یم
    0.45
    Nunca
    0.45
    راجع
    0.45
    regression
    0.45
    밟
    0.45
    辎
    0.45
    רים
    0.44
    분
    0.44
    POSITIVE LOGITS
     en
    0.52
     straw
    0.49
     sleigh
    0.48
     borough
    0.48
     nó
    0.47
     হার
    0.47
     ज़्यादा
    0.47
     Town
    0.46
     nz
    0.45
     hok
    0.45
    Activations Density 0.001%

    No Known Activations