© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56517
    Prev
    Next
    INDEX
    Explanations

    methods on the

    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
    t
    0.62
    tor
    0.53
    re
    0.50
    an
    0.50
    ere
    0.50
    pre
    0.49
    invest
    0.49
    inin
    0.48
    per
    0.46
    ana
    0.46
    POSITIVE LOGITS
     moles
    0.46
     '+':
    0.46
    Ἥ
    0.46
    ונים
    0.45
    สำหรับ
    0.45
     যাতে
    0.43
     getUsersBy
    0.43
    เพื่อให้
    0.42
    瀉
    0.42
     dưới
    0.42
    Activations Density 0.014%

    No Known Activations