© 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. 14435
    Prev
    Next
    INDEX
    Explanations

    mentioned previously or above

    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
     are
    1.40
    are
    1.24
     it
    1.19
     όλ
    1.02
    ح
    0.99
    ٠
    0.99
    illion
    0.98
     a
    0.98
     In
    0.97
     ا
    0.96
    POSITIVE LOGITS
    t
    1.91
    م
    1.68
    ר
    1.57
    К
    1.55
    m
    1.49
    ம்
    1.45
    ર
    1.42
    म
    1.40
    ли
    1.38
    ко
    1.31
    Activations Density 0.013%

    No Known Activations