© 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. 71696
    Prev
    Next
    INDEX
    Explanations

    earnings, before, soon, reviews, associated, risks

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

    automata, use after, dies, hack

    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
     এতটা
    0.52
    的分
    0.50
     bhavati
    0.47
    emap
    0.46
    )¶
    0.45
     }()
    0.45
     अड्
    0.45
     treści
    0.45
    actica
    0.45
    lių
    0.44
    POSITIVE LOGITS
     estimates
    0.50
    sion
    0.50
    s
    0.50
     for
    0.49
    uth
    0.46
     Omer
    0.44
     après
    0.44
    ↵↵↵
    0.43
    öner
    0.43
     apparel
    0.42
    Activations Density 0.000%

    No Known Activations