© 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. 243936
    Prev
    Next
    INDEX
    Explanations

    multilingual characters and punctuation

    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
    ㆍ
    0.53
    ı
    0.45
    Ŝ
    0.44
    <!
    0.44
     turb
    0.43
     kdy
    0.43
    loadNpmTasks
    0.42
     dlatego
    0.42
    ̂
    0.42
    Ꮯ
    0.42
    POSITIVE LOGITS
    త్వం
    0.50
     問
    0.46
     جري
    0.46
    壁
    0.45
     کنی
    0.44
     गिरि
    0.44
    dcsset
    0.43
    參数
    0.43
     CANT
    0.43
    神的
    0.43
    Activations Density 0.000%

    No Known Activations