© 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. 126559
    Prev
    Next
    INDEX
    Explanations

    numbers, foreign, unusual

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

    eyes, tremors, Garlic, Risk, Chorus, Similar

    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
     PA
    0.52
    憧
    0.50
    0.48
     Anil
    0.47
     b
    0.47
     PI
    0.47
    wf
    0.45
     ง
    0.45
     mak
    0.44
     Cray
    0.44
    POSITIVE LOGITS
    岛
    0.50
     সহজাত
    0.50
     diminishing
    0.48
     diminishes
    0.47
    쾨
    0.46
    লাইয়া
    0.46
    åg
    0.45
     cuándo
    0.45
    ério
    0.44
    fk
    0.43
    Activations Density 0.000%

    No Known Activations