© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10485
    Prev
    Next
    INDEX
    Explanations

    in case

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

    situations and cases

    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_40_width_16k_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
    围绕
    0.45
    isive
    0.39
    CTION
    0.37
     CustB
    0.37
     (°
    0.37
    वले
    0.37
    THING
    0.37
    muster
    0.36
    グ
    0.36
     লইয়
    0.35
    POSITIVE LOGITS
     cases
    2.77
     caso
    2.72
     kasus
    2.47
     casos
    2.45
     Cases
    2.41
    กรณี
    2.41
    cases
    2.38
     случаев
    2.38
     case
    2.36
     경우
    2.34
    Activations Density 0.482%

    No Known Activations