© 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. 42202
    Prev
    Next
    INDEX
    Explanations

    expressions of hate and dislike

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

    hate and dislike

    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
     wellknown
    0.46
    er
    0.45
     velit
    0.45
    म्मा
    0.44
     Cra
    0.43
     devoured
    0.41
    狂
    0.41
    各项
    0.40
    arder
    0.40
     wären
    0.40
    POSITIVE LOGITS
     separators
    0.51
     покрытия
    0.46
     వ్యక్
    0.46
     indentation
    0.45
     מט
    0.45
     Periods
    0.45
     justifying
    0.44
    Periods
    0.44
     periods
    0.43
     justifications
    0.43
    Activations Density 0.032%

    No Known Activations