© 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. 17828
    Prev
    Next
    INDEX
    Explanations

    sell signal

    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
    ية
    1.51
    de
    1.47
    ле
    1.44
    на
    1.34
    k
    1.20
     can
    1.20
    berly
    1.20
    ب
    1.20
    ne
    1.19
     for
    1.16
    POSITIVE LOGITS
    는
    1.68
    是
    1.28
    は
    1.17
    <h2>
    1.12
    ร
    1.08
    in
    1.05
    ’
    1.05
    是對
    1.03
    <h3>
    0.98
    I
    0.93
    Activations Density 0.010%

    No Known Activations