© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 175092
    Prev
    Next
    INDEX
    Explanations

    corporate initiatives, deadbeat dad walks

    np_acts-logits-general · gemini-2.5-flash-lite

    specializing in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perceive
    0.50
     아래
    0.49
     rusk
    0.46
     काला
    0.45
     e
    0.44
    켐
    0.44
     chief
    0.43
    kcal
    0.42
     typographical
    0.42
     aide
    0.42
    POSITIVE LOGITS
    नै
    0.64
    ج
    0.54
    ្
    0.53
    جاز
    0.50
    پ
    0.49
    鸫
    0.49
    ْ
    0.48
    ط
    0.48
    ون
    0.47
    ن
    0.47
    Activations Density 0.000%

    No Known Activations