© 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. 52715
    Prev
    Next
    INDEX
    Explanations

    however

    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
    блиоте
    0.46
    aternary
    0.42
     חש
    0.42
    ணமாக
    0.41
    ፈ
    0.41
    時尚
    0.40
    夻
    0.39
     முயற்
    0.39
     έχει
    0.39
     কাঠের
    0.38
    POSITIVE LOGITS
    Kep
    0.45
     wok
    0.44
     sanciones
    0.44
     indeks
    0.43
    インタビュー
    0.42
    %,
    0.42
    MI
    0.42
    Ꮳ
    0.40
     polskich
    0.40
    ۱
    0.40
    Activations Density 0.019%

    No Known Activations