© 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. 86822
    Prev
    Next
    INDEX
    Explanations

    earth's geological mantle

    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
    0.71
    .
    0.69
     can
    0.67
    2
    0.61
    s
    0.61
    ার
    0.59
     will
    0.59
    <0x91>
    0.59
    t
    0.59
    1
    0.55
    POSITIVE LOGITS
     pakai
    0.68
    atsioon
    0.68
    쓰
    0.68
     buono
    0.67
     montañas
    0.65
     bū
    0.65
    خی
    0.65
    対処
    0.65
     manglid
    0.64
     brunâtre
    0.64
    Activations Density 0.001%

    No Known Activations