© 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. 109154
    Prev
    Next
    INDEX
    Explanations

    log entry and filtering

    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
    ’।
    0.50
     ፡፡
    0.49
     ଅ
    0.48
     développement
    0.46
     arrondi
    0.46
    phalt
    0.46
     récomp
    0.46
    ።
    0.46
     previsto
    0.45
    ओं
    0.45
    POSITIVE LOGITS
    MY
    0.46
    Didn
    0.44
    Fields
    0.43
     WTF
    0.43
    ಿತ
    0.43
    Factory
    0.42
    م
    0.41
    Where
    0.40
    WT
    0.40
    ه
    0.40
    Activations Density 0.000%

    No Known Activations