© 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. 47458
    Prev
    Next
    INDEX
    Explanations

    end of sentence

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

    future iteration

    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
    ສະ
    0.44
    Firstly
    0.43
     깜
    0.43
    쭌
    0.43
     Firstly
    0.41
     displeasure
    0.40
    사장
    0.40
     خور
    0.40
     sadness
    0.39
     первый
    0.39
    POSITIVE LOGITS
     类
    0.45
    类
    0.43
    更大的
    0.41
     کنه
    0.41
     这些
    0.40
     做
    0.40
    也會
    0.39
    ambahan
    0.39
     输出
    0.39
     Иногда
    0.39
    Activations Density 0.002%

    No Known Activations