© 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. 60874
    Prev
    Next
    INDEX
    Explanations

    sure you

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

    past outcomes and future 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
    ^{*}(\
    0.48
     Adhesive
    0.48
    ^{*}(
    0.47
     adhesives
    0.45
     функції
    0.44
    projectView
    0.44
    க்
    0.44
    Receipt
    0.44
    礼物
    0.43
    нэт
    0.42
    POSITIVE LOGITS
     Deja
    0.46
     [...
    0.46
    ちな
    0.45
    උ
    0.45
    ･･･
    0.44
    めに
    0.43
     Johnny
    0.43
     Meredith
    0.42
     }^{
    0.42
     tekr
    0.42
    Activations Density 0.000%

    No Known Activations