© 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. 257545
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     tabular
    0.60
     factorial
    0.54
     candid
    0.46
     clerical
    0.45
    colspan
    0.45
    <0x80>
    0.44
     benign
    0.44
     solicitar
    0.44
     turnkey
    0.44
     exif
    0.44
    POSITIVE LOGITS
     Seahawks
    0.48
    萨
    0.43
     Beasts
    0.42
     Warriors
    0.41
    स्कूल
    0.41
     Beast
    0.40
    මත්
    0.39
    爆发
    0.39
    🦁
    0.38
    𝓪
    0.38
    Activations Density 0.008%

    No Known Activations