© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 40704
    Prev
    Next
    INDEX
    Explanations

    offense and defense in sports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AN
    0.94
    UR
    0.86
    AR
    0.79
    AL
    0.79
    P
    0.76
    AO
    0.76
    IN
    0.75
    UP
    0.75
    X
    0.73
    ER
    0.71
    POSITIVE LOGITS
     offense
    0.69
     जास्त
    0.66
     அந்த
    0.66
     offenses
    0.61
    秙
    0.61
    )$
    0.59
     permitting
    0.59
     Banglades
    0.59
     अगदी
    0.59
    ндагы
    0.58
    Activations Density 0.002%

    No Known Activations