© 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. 135464
    Prev
    Next
    INDEX
    Explanations

    garage area or have the

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

    managing actions and states

    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
    2
    0.61
    (
    0.60
    1
    0.48
     notamment
    0.46
     BN
    0.46
    、
    0.46
     (
    0.45
     for
    0.45
     poignant
    0.45
    有关
    0.44
    POSITIVE LOGITS
     それぞれ
    0.54
     器
    0.51
     dragState
    0.48
    FrameLength
    0.47
     findAll
    0.47
     흐
    0.46
    🄴
    0.46
    kfollowers
    0.46
     الده
    0.45
     Mikolai
    0.44
    Activations Density 0.001%

    No Known Activations