© 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. 165272
    Prev
    Next
    INDEX
    Explanations

    kids activity providers

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

    celebrate and hand

    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
    偐
    0.59
    䚯
    0.58
     رنز
    0.57
    ᴙ
    0.57
     거짓
    0.54
     यर
    0.53
    ių
    0.53
    ἓ
    0.52
    ۶
    0.51
    䒽
    0.51
    POSITIVE LOGITS
    Validate
    0.47
    Slip
    0.46
     la
    0.45
     voluntarily
    0.44
     mitigate
    0.43
     lightly
    0.43
    Rights
    0.43
    Fish
    0.43
     liberty
    0.42
    Relative
    0.42
    Activations Density 0.001%

    No Known Activations