© 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. 27586
    Prev
    Next
    INDEX
    Explanations

    daily returns

    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
     ការ
    0.44
     విషయంలో
    0.42
     anderer
    0.41
    ära
    0.41
     μια
    0.40
    ils
    0.40
     considerazione
    0.40
    ڇ
    0.40
     boh
    0.39
     বহন
    0.39
    POSITIVE LOGITS
    стам
    0.44
    $,
    0.41
    נו
    0.40
    You
    0.39
     സോ
    0.39
    (),
    0.38
     totaled
    0.38
    with
    0.38
     alongside
    0.38
    מ
    0.38
    Activations Density 0.001%

    No Known Activations