© 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. 49334
    Prev
    Next
    INDEX
    Explanations

    checking calculation or correctness

    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
    $;
    0.47
    ',(
    0.43
    When
    0.42
    avanje
    0.42
    Repo
    0.40
     Приступљено
    0.40
    hese
    0.40
    January
    0.39
    '});
    0.39
    ૧
    0.39
    POSITIVE LOGITS
    酶
    0.44
    ACT
    0.40
     lactate
    0.40
     rosette
    0.39
     plasma
    0.39
     protein
    0.39
     alters
    0.38
     Phosphate
    0.38
     producing
    0.38
     সুদ
    0.38
    Activations Density 0.001%

    No Known Activations