© 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. 59266
    Prev
    Next
    INDEX
    Explanations

    might there be

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

    trusting developers or creators

    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
     görünt
    0.44
    Nếu
    0.43
    Transforms
    0.43
    HashCode
    0.43
    문의
    0.41
    Jeśli
    0.41
    ↵↵↵↵↵↵↵
    0.41
    Ẩ
    0.40
    لو
    0.39
     उड़
    0.39
    POSITIVE LOGITS
     Evening
    0.47
    young
    0.47
     যাঁরা
    0.46
     সেলিম
    0.44
     Lyndon
    0.43
    us
    0.43
    of
    0.42
    sheep
    0.42
     Ashram
    0.42
    on
    0.42
    Activations Density 0.000%

    No Known Activations