© 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. 2039
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by sentence starters

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

    multi-language technical terms

    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
    Capt
    0.49
    capt
    0.47
    St
    0.41
     Capt
    0.39
    autocomplete
    0.39
    Ẩ
    0.38
    nG
    0.38
    Ang
    0.38
    йл
    0.38
    тап
    0.37
    POSITIVE LOGITS
    廣場
    0.46
     foresee
    0.43
     setzen
    0.43
     ليس
    0.41
     !***
    0.41
     መድ
    0.41
     কেন্দ্র
    0.40
    itäts
    0.39
     sąd
    0.39
     არს
    0.39
    Activations Density 0.000%

    No Known Activations