© 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. 103458
    Prev
    Next
    INDEX
    Explanations

    google ads ad copy

    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
     If
    0.50
    ματο
    0.45
     مهما
    0.44
    פל
    0.44
    敀
    0.44
    κού
    0.43
    م
    0.43
    溦
    0.43
    䓶
    0.42
    ριν
    0.41
    POSITIVE LOGITS
    Lateral
    0.54
    lateral
    0.49
     metropolitan
    0.48
    incidence
    0.47
     Perfecto
    0.47
    cedented
    0.46
    sli
    0.46
    therefore
    0.46
    ्यर
    0.46
    clothes
    0.46
    Activations Density 0.001%

    No Known Activations