© 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. 23217
    Prev
    Next
    INDEX
    Explanations

    legalistic context

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

    specific procedures

    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
    。
    0.47
     \%
    0.45
     manuals
    0.43
     loft
    0.42
     OFFICES
    0.42
    σεων
    0.42
    мага
    0.41
     CSS
    0.40
    。(
    0.40
     modules
    0.39
    POSITIVE LOGITS
    ക
    0.56
    k
    0.48
     ilegal
    0.47
    کان
    0.47
    üyor
    0.46
     disbelief
    0.46
    ethoscope
    0.45
     Albu
    0.45
     ایمان
    0.44
     excitedly
    0.44
    Activations Density 0.000%

    No Known Activations