© 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. 32980
    Prev
    Next
    INDEX
    Explanations

    philosophy, practices, or systems

    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
     .*
    0.33
    !.
    0.32
    ®.
    0.30
    <unused2138>
    0.30
     każde
    0.30
    .
    0.29
     naprawdę
    0.29
     likeness
    0.29
    aisesti
    0.28
    .¹
    0.28
    POSITIVE LOGITS
     for
    0.34
     that
    0.33
    etc
    0.32
    ಮೊ
    0.31
    that
    0.30
     για
    0.30
    για
    0.29
    for
    0.29
     Recursos
    0.29
     frustrate
    0.28
    Activations Density 0.021%

    No Known Activations