© 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. 9830
    Prev
    Next
    INDEX
    Explanations

    names after slashes or semicolons

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

    authorship and editing information

    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
    llam
    0.54
    :-
    0.45
    가의
    0.44
     llamadas
    0.40
    Roaming
    0.40
    函数
    0.40
     lọ
    0.39
    会对
    0.39
     রাষ্ট্রীয়
    0.39
     власти
    0.39
    POSITIVE LOGITS
     [
    0.60
    with
    0.46
     written
    0.44
    featuring
    0.44
     edited
    0.43
     Written
    0.42
     with
    0.41
     ...,
    0.39
    sponsored
    0.39
     Includes
    0.38
    Activations Density 0.007%

    No Known Activations