© 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. 6952
    Prev
    Next
    INDEX
    Explanations

    Crisis Text Line, MOVEit Transfer, UserTesting, Alpha Vantage

    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
    {
    0.47
    ili
    0.47
    í
    0.45
    ր
    0.45
    glomer
    0.44
    <0x99>
    0.43
    <0xA1>
    0.43
    نا
    0.42
    ur
    0.42
    ному
    0.42
    POSITIVE LOGITS
     is
    0.61
     the
    0.59
     jeopard
    0.52
    ك
    0.51
     our
    0.51
     gets
    0.50
     contraband
    0.50
     Día
    0.49
     Rihanna
    0.49
    ה
    0.49
    Activations Density 0.343%

    No Known Activations