© 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. 245324
    Prev
    Next
    INDEX
    Explanations

    religious or legal clauses

    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
     Dense
    0.53
     Brilliant
    0.52
     magnis
    0.51
     Colors
    0.49
     Beaut
    0.49
    c
    0.49
    it
    0.48
     it
    0.47
     Profes
    0.46
     Racer
    0.46
    POSITIVE LOGITS
    VHS
    0.49
    ópez
    0.47
    equival
    0.46
    NH
    0.46
    MeOH
    0.45
    insulated
    0.45
    FIFO
    0.44
    သင်
    0.44
    INFE
    0.43
    VOC
    0.43
    Activations Density 0.001%

    No Known Activations