© 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. 14850
    Prev
    Next
    INDEX
    Explanations

    question marks and exclamation marks

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

    structured text with lists and formatting

    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
    on
    0.43
    hi
    0.40
    r
    0.39
    h
    0.39
    so
    0.38
    set
    0.38
    con
    0.38
    ਰ
    0.38
    il
    0.37
    n
    0.37
    POSITIVE LOGITS
     虽然
    0.41
    এশিয়া
    0.41
     মুক্তিযোদ্ধারা
    0.40
     Bởi
    0.39
     はい
    0.39
     getUserBy
    0.38
     ঐতি
    0.38
    াকর্ম
    0.38
     由于
    0.37
     বেশিরভাগ
    0.37
    Activations Density 0.010%

    No Known Activations