© 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. 168891
    Prev
    Next
    INDEX
    Explanations

    data, link, bonds, dimensions

    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
     reflected
    0.42
     was
    0.41
     D
    0.40
    D
    0.40
     felt
    0.39
    :
    0.39
     de
    0.38
     dich
    0.38
    д
    0.37
     MB
    0.37
    POSITIVE LOGITS
    iót
    0.52
    नेत
    0.51
    ेंद्रीय
    0.45
     سعودی
    0.44
    ovies
    0.43
     заявил
    0.43
    ॉम
    0.41
    नेता
    0.41
    䬲
    0.41
    NSMutableArray
    0.40
    Activations Density 0.004%

    No Known Activations