© 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. 40-GEMMASCOPE-2-RES-262K
    7. 9416
    Prev
    Next
    INDEX
    Explanations

    Lyft, Langley, Leonardo, LFS

    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_40_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
    გი
    0.38
     nešto
    0.37
    ᵕ
    0.37
    ...");
    0.36
    告知
    0.35
     morte
    0.35
    ”:
    0.35
    :"))
    0.35
    酌
    0.35
    ⠛
    0.35
    POSITIVE LOGITS
     LC
    0.51
     UL
    0.49
     LF
    0.48
     LRT
    0.48
     LCS
    0.46
     L
    0.45
     LMS
    0.45
     LIC
    0.45
    newL
    0.44
     LV
    0.42
    Activations Density 0.172%

    No Known Activations