© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 31735
    Prev
    Next
    INDEX
    Explanations

    describing appearance after "look"

    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
     in
    0.90
    ],
    0.84
     looking
    0.78
     an
    0.75
     inaugur
    0.69
    ﺵ
    0.69
     after
    0.68
    も含
    0.68
     are
    0.67
     oppure
    0.67
    POSITIVE LOGITS
    д
    0.78
    و
    0.76
    د
    0.76
    ل
    0.64
    aa
    0.61
    ป่วย
    0.61
    ans
    0.61
    ung
    0.59
    b
    0.59
        
    0.59
    Activations Density 0.010%

    No Known Activations