© 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. 6257
    Prev
    Next
    INDEX
    Explanations

    digit or number

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

    digits and building blocks

    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
    tu
    0.51
    tit
    0.48
    a
    0.47
    tab
    0.47
    tal
    0.47
    A
    0.47
    tib
    0.46
    se
    0.44
     prag
    0.44
     turned
    0.44
    POSITIVE LOGITS
     للح
    0.48
     রিলিফ
    0.48
    後ろ
    0.47
    itabbam
    0.47
    ானி
    0.47
     retShape
    0.44
    itriangular
    0.43
     участка
    0.42
    紗
    0.42
    䊂
    0.42
    Activations Density 0.000%

    No Known Activations