© 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. 31-GEMMASCOPE-2-RES-262K
    7. 4250
    Prev
    Next
    INDEX
    Explanations

    leet speak or gibberish texts

    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_31_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
    0.41
     grandma
    0.34
     is
    0.33
    s
    0.33
     was
    0.32
     proces
    0.32
    you
    0.32
     nasty
    0.31
     passen
    0.31
     pasan
    0.31
    POSITIVE LOGITS
    و
    0.29
     fellowships
    0.29
     দৃঢ়
    0.28
    癹
    0.28
    wirkung
    0.28
    <>());
    0.28
    -​
    0.28
    هداف
    0.27
    ق
    0.27
    <unused717>
    0.27
    Activations Density 0.001%

    No Known Activations