© 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. 3062
    Prev
    Next
    INDEX
    Explanations

    categorized by focus

    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
    >∕
    0.44
    िओ
    0.42
    <unused2189>
    0.41
     नंबर
    0.41
     tai
    0.41
     pretzels
    0.41
     फाउंड
    0.41
    ugging
    0.41
     प्रारूप
    0.41
    POSITIVE LOGITS
    nV
    0.46
    Y
    0.46
    HTML
    0.46
     plainly
    0.45
     authorize
    0.45
    0.44
    DOCUMENT
    0.44
     nejen
    0.44
    punkte
    0.42
    ędzie
    0.42
    Activations Density 0.014%

    No Known Activations