© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 4164
    Prev
    Next
    INDEX
    Explanations

    contact us today

    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
    m
    0.69
    an
    0.65
    on
    0.59
    at
    0.59
    k
    0.56
     slits
    0.55
    not
    0.54
    OR
    0.53
    t
    0.53
    a
    0.53
    POSITIVE LOGITS
    !”
    0.57
    اللہ
    0.55
     ”,
    0.52
    𝒔
    0.52
     নিয়ন্ত্রণে
    0.51
     Букмекерлар
    0.51
     tentunya
    0.51
    そして
    0.50
    と
    0.50
    𝗴
    0.50
    Activations Density 0.010%

    No Known Activations