Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 7298
    Prev
    Next
    INDEX
    Explanations

    child exploitation

    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
    as
    0.71
    to
    0.61
    ul
    0.59
    is
    0.59
    ي
    0.54
    on
    0.51
    doesn
    0.50
    ла
    0.48
    formerly
    0.47
    á
    0.47
    POSITIVE LOGITS
     an
    0.45
     I
    0.37
     .
    0.36
    <0x0D>
    0.33
    ;
    0.32
     filepath
    0.31
     varsity
    0.31
     filePath
    0.30
     such
    0.30
    sville
    0.30
    Activations Density 0.654%

    No Known Activations