© 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. 120173
    Prev
    Next
    INDEX
    Explanations

    cut, hanging, MAT, Principal

    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
    j
    0.76
    అ
    0.67
    to
    0.66
    는
    0.64
    gold
    0.63
    다
    0.61
    Richard
    0.58
    지
    0.58
    game
    0.57
    gene
    0.57
    POSITIVE LOGITS
    ى
    0.76
    ụ
    0.68
     cenas
    0.66
     citas
    0.64
    цами
    0.64
     ferrovi
    0.64
     terrib
    0.64
     χρό
    0.63
     incompar
    0.63
     curtailed
    0.62
    Activations Density 0.000%

    No Known Activations