© 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. 54796
    Prev
    Next
    INDEX
    Explanations

    not consumed itself

    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
    पर्या
    0.46
    Accessories
    0.45
    伱
    0.44
    了他
    0.43
    śli
    0.43
    تر
    0.41
    एफसी
    0.41
    Setting
    0.41
    éma
    0.41
    िशन
    0.41
    POSITIVE LOGITS
     retiring
    0.48
     દરમ
    0.47
     hurting
    0.44
     nikdy
    0.44
     અને
    0.43
     ഒഴ
    0.43
    廢
    0.43
     那麼
    0.42
    kelijke
    0.42
     meltdown
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.