© 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. 122134
    Prev
    Next
    INDEX
    Explanations

    multi-language short forms

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

    ECC errors

    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
    ผ่าน
    0.46
    צע
    0.45
    טי
    0.43
    視覺
    0.41
    ぞれ
    0.41
    цій
    0.40
    櫃
    0.40
    सी
    0.40
    通過
    0.40
    潦
    0.40
    POSITIVE LOGITS
    im
    0.52
    em
    0.47
     आल्सो
    0.47
    ol
    0.46
    ok
    0.46
    有可能
    0.46
    olées
    0.45
    もあり
    0.45
    hamilan
    0.45
    also
    0.45
    Activations Density 0.000%

    No Known Activations