© 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. 39078
    Prev
    Next
    INDEX
    Explanations

    globe awards

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

    list formatting definition

    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
     ۴
    0.51
    運び
    0.49
     ይህ
    0.48
     という
    0.48
     സഹ
    0.48
     Bruder
    0.48
     스트
    0.48
    兗
    0.48
    計測
    0.48
    transfected
    0.47
    POSITIVE LOGITS
    ID
    0.52
    res
    0.48
    stav
    0.48
    IME
    0.47
    Screen
    0.46
    Architect
    0.46
    RO
    0.46
    Estim
    0.46
     antr
    0.45
    Qué
    0.44
    Activations Density 0.000%

    No Known Activations