© 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. 25492
    Prev
    Next
    INDEX
    Explanations

    written consent or agreement

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

    CI/CD pipelines

    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
    کنش
    0.51
    ک
    0.45
     یہودیوں
    0.45
    یرو
    0.44
     بھول
    0.43
     mục
    0.41
     ফেলা
    0.41
    ombie
    0.40
    운데
    0.39
    ربی
    0.39
    POSITIVE LOGITS
     沒有
    0.55
     peč
    0.54
     szól
    0.53
     wundersch
    0.52
     osob
    0.51
    𝖺
    0.51
     krás
    0.50
     يقول
    0.49
    𝗈
    0.49
     إِن
    0.49
    Activations Density 0.000%

    No Known Activations