© 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. 157426
    Prev
    Next
    INDEX
    Explanations

    regulations differ

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

    ways it is described

    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
     Bump
    0.46
    was
    0.46
    _.
    0.44
     Jo
    0.44
    Jo
    0.43
     Forge
    0.43
     Account
    0.43
     Culture
    0.43
     Treasury
    0.43
     Picture
    0.42
    POSITIVE LOGITS
    ْر
    0.55
     являются
    0.50
    ット
    0.50
    ен
    0.49
    )$\\
    0.49
    ק
    0.49
    )(-
    0.48
    дето
    0.47
     т
    0.46
     позволяют
    0.46
    Activations Density 0.001%

    No Known Activations