© 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. 258121
    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
     segmented
    0.49
     granular
    0.46
     Fuzzy
    0.45
     keratin
    0.44
     g
    0.44
    getBoolean
    0.44
     mish
    0.44
     token
    0.43
     Token
    0.43
     ۸
    0.43
    POSITIVE LOGITS
    𝚝
    0.53
    тре
    0.50
    Climate
    0.49
    Var
    0.49
     ব্রিজ
    0.49
    сай
    0.48
    ть
    0.47
     liées
    0.47
    ユー
    0.46
    те
    0.46
    Activations Density 0.001%

    No Known Activations