© 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. 239218
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

    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
    ro
    0.45
    let
    0.44
    akkhand
    0.43
    dou
    0.41
    es
    0.41
    <0x80>
    0.40
    atomic
    0.39
     letzte
    0.39
    factorial
    0.39
    ર
    0.39
    POSITIVE LOGITS
     αί
    0.53
     hagas
    0.53
    परीक्षा
    0.50
     FOLLOW
    0.50
     따라
    0.49
     Це
    0.48
    
    0.47
     ensayos
    0.47
     siguió
    0.46
     सबको
    0.46
    Activations Density 0.000%

    No Known Activations