© 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. 3720
    Prev
    Next
    INDEX
    Explanations

    Assume

    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
    0.66
    '
    0.61
     on
    0.54
     with
    0.52
    AN
    0.49
     לאחר
    0.48
     is
    0.47
    氇
    0.46
    ECO
    0.44
    arming
    0.43
    POSITIVE LOGITS
    u
    0.93
    ла
    0.84
    an
    0.77
    h
    0.76
    er
    0.69
    ர்
    0.69
    ون
    0.66
    на
    0.66
    л
    0.65
    ри
    0.64
    Activations Density 0.558%

    No Known Activations