© 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. 61218
    Prev
    Next
    INDEX
    Explanations

    have decent credit

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

    vegetables and perceptions

    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
    不满
    0.48
     dout
    0.48
    nje
    0.47
    ifte
    0.46
    −
    0.46
     وفي
    0.45
     czasu
    0.45
    ceq
    0.45
    ął
    0.45
    ו
    0.45
    POSITIVE LOGITS
     indigenous
    0.47
     Ró
    0.44
     Organized
    0.44
    ेश्व
    0.44
     hedging
    0.43
     arugula
    0.43
     संचालित
    0.43
     paintbrush
    0.43
     rebranding
    0.42
     hedgehog
    0.41
    Activations Density 0.000%

    No Known Activations