© 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. 7744
    Prev
    Next
    INDEX
    Explanations

    purpose or context

    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
    in
    0.45
    y
    0.35
    es
    0.33
    I
    0.32
    ed
    0.31
    e
    0.30
    o
    0.29
    O
    0.27
    as
    0.26
    ing
    0.26
    POSITIVE LOGITS
     a
    0.26
    ዚህ
    0.23
     be
    0.22
    ked
    0.22
    što
    0.21
     sucedido
    0.21
    geries
    0.21
     personas
    0.20
     приобре
    0.20
    твори
    0.20
    Activations Density 0.539%

    No Known Activations