© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10482
    Prev
    Next
    INDEX
    Explanations

    AutoTokenizer, AutoModelForCausalLM

    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
    isserie
    0.38
    arious
    0.38
    arial
    0.38
     KQkq
    0.38
     bono
    0.38
     ジョ
    0.38
    バ
    0.38
    irikan
    0.37
    接続
    0.37
    隹
    0.37
    POSITIVE LOGITS
     AUT
    0.64
     Aut
    0.63
     Auto
    0.63
     auto
    0.63
     Autob
    0.59
    Auto
    0.57
     AUTO
    0.57
    AUT
    0.57
     otomatik
    0.55
    Aut
    0.54
    Activations Density 0.017%

    No Known Activations