© 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. 41853
    Prev
    Next
    INDEX
    Explanations

    valid things

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

    invalid input detection

    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
    it
    0.87
    a
    0.77
    ed
    0.73
    TON
    0.73
    ot
    0.72
    ént
    0.72
    v
    0.71
     Người
    0.69
    u
    0.69
    ियों
    0.68
    POSITIVE LOGITS
     valid
    1.06
     isValid
    0.94
     validity
    0.87
     vál
    0.80
    valid
    0.77
     valide
    0.75
     वैध
    0.74
     Valid
    0.73
    Valid
    0.72
    да
    0.71
    Activations Density 0.010%

    No Known Activations