© 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. 189811
    Prev
    Next
    INDEX
    Explanations

    names and associated actions/details

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

    skill, progress, systems, analysis

    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
    to
    0.50
    dzie
    0.48
    k
    0.47
    putar
    0.46
     ketua
    0.45
    centos
    0.45
    って
    0.45
    ้อง
    0.45
    ceq
    0.45
    then
    0.44
    POSITIVE LOGITS
     azonban
    0.44
    📏
    0.44
    📐
    0.43
     arrête
    0.42
     Fishing
    0.42
    OrderDetail
    0.41
     umiejęt
    0.41
    ವ
    0.41
     conformément
    0.40
     Proficiency
    0.40
    Activations Density 0.001%

    No Known Activations