© 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. 222102
    Prev
    Next
    INDEX
    Explanations

    `!` followed by `=""` or `Again`

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

    checking for empty or invalid inputs

    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
    ”।
    0.54
    К
    0.54
    ن
    0.54
    가
    0.54
    자가
    0.53
    ק
    0.52
    ну
    0.51
    т
    0.50
    １
    0.50
    ną
    0.50
    POSITIVE LOGITS
    stehen
    0.55
    េច
    0.52
    org
    0.49
    cken
    0.49
     parturient
    0.48
     ឬ
    0.47
     அல்லது
    0.47
    hma
    0.47
     तरह
    0.46
     सारे
    0.46
    Activations Density 0.000%

    No Known Activations