© 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. 2310
    Prev
    Next
    INDEX
    Explanations

    compound nouns and concepts

    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
    paced
    0.37
     Euclidean
    0.35
    s
    0.35
    cm
    0.34
    methylsulfanyl
    0.34
     pharmacological
    0.33
    ზრ
    0.33
    attrib
    0.33
    srand
    0.33
    %%%%%%%%%%%%%%%%
    0.33
    POSITIVE LOGITS
    之类的
    0.50
    などに
    0.44
     või
    0.42
    يسي
    0.42
     أو
    0.42
     cárcel
    0.41
     или
    0.41
     hätte
    0.41
     או
    0.40
     কিংবা
    0.40
    Activations Density 0.081%

    No Known Activations