© 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. 174735
    Prev
    Next
    INDEX
    Explanations

    probe tester

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

    potential actions or states

    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
    бав
    0.50
    柤
    0.49
    헙
    0.49
     LAYER
    0.48
    विता
    0.47
    гра
    0.46
    欹
    0.46
    кри
    0.46
    棫
    0.45
    녘
    0.45
    POSITIVE LOGITS
     studi
    0.57
     kaum
    0.55
     zoo
    0.49
     list
    0.47
     drugi
    0.46
    zoo
    0.46
    ing
    0.45
     حی
    0.45
     pep
    0.44
     cag
    0.44
    Activations Density 0.000%

    No Known Activations