© 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. 30662
    Prev
    Next
    INDEX
    Explanations

    torch tutorials

    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
    Attorney
    0.43
    Sic
    0.43
    Athens
    0.42
    astus
    0.41
    㚅
    0.40
    acted
    0.40
     сі
    0.39
    manha
    0.38
     ჟ
    0.38
     ჩატი
    0.38
    POSITIVE LOGITS
     Dave
    0.40
     Catering
    0.38
     St
    0.37
    ká
    0.37
     Wink
    0.37
     Tutorial
    0.36
     Appointments
    0.36
     dave
    0.36
     tutorial
    0.36
     Quiz
    0.36
    Activations Density 0.000%

    No Known Activations