© 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. 11909
    Prev
    Next
    INDEX
    Explanations

    links to online articles

    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
     energético
    0.43
     annealing
    0.41
     ہتھی
    0.41
    分け
    0.39
    ಲ್ಯ
    0.39
    ᅧ
    0.39
    avasena
    0.38
    soe
    0.38
     ندير
    0.38
     انر
    0.38
    POSITIVE LOGITS
     Or
    0.40
    Teacher
    0.38
    Discovery
    0.38
     Click
    0.38
     Herb
    0.37
    D
    0.37
     To
    0.37
    Or
    0.36
    Scroll
    0.36
    Herb
    0.36
    Activations Density 0.000%

    No Known Activations