© 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. 19986
    Prev
    Next
    INDEX
    Explanations

    website addresses

    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
     a
    1.24
    >
    1.11
     it
    1.04
     he
    1.00
    ون
    0.96
    بية
    0.96
    కి
    0.94
     that
    0.92
     you
    0.89
    0.88
    POSITIVE LOGITS
    리
    1.30
    의
    1.09
    ро
    1.02
     domeni
    1.02
    の
    1.01
    ो
    0.95
    ک
    0.95
    www
    0.94
     conness
    0.94
    ब्ल्यू
    0.94
    Activations Density 0.036%

    No Known Activations