© 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-65K
    7. 1446
    Prev
    Next
    INDEX
    Explanations

    establishing a theme

    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_65k_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
     iyong
    0.24
     reali
    0.24
     acara
    0.24
     you
    0.24
     alright
    0.24
     reto
    0.24
     your
    0.23
    你
    0.23
     anto
    0.23
     obtenir
    0.23
    POSITIVE LOGITS
    and
    0.36
     for
    0.33
    на
    0.32
    ap
    0.29
    ма
    0.29
    for
    0.28
    ку
    0.28
    et
    0.28
    кла
    0.27
    am
    0.27
    Activations Density 0.504%

    No Known Activations