© 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. 36315
    Prev
    Next
    INDEX
    Explanations

    She was

    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
    פ
    0.45
     힘들
    0.44
     współpracy
    0.44
     회사
    0.43
    ঙ্গার
    0.42
     тща
    0.42
    liert
    0.42
    Dieter
    0.40
     ООО
    0.40
     flatter
    0.40
    POSITIVE LOGITS
    रुण
    0.59
    KeyboardMarkup
    0.57
     notes
    0.54
     entsprechenden
    0.49
    痙
    0.49
     games
    0.48
     également
    0.47
    感染
    0.45
     कोविड
    0.45
     corresponds
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.