© 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. 222974
    Prev
    Next
    INDEX
    Explanations

    share experience and information

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

    magnetic alignment, sedimentary facies

    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
    updateConfirm
    0.50
     गांधी
    0.50
     请
    0.50
     मैदान
    0.48
    btnClose
    0.48
     كبيرة
    0.47
    ນີ້
    0.47
    ൺ
    0.47
     موږ
    0.47
     fabricantes
    0.46
    POSITIVE LOGITS
     bless
    0.55
    r
    0.54
     used
    0.50
     scratch
    0.48
     spider
    0.47
     mod
    0.47
     hack
    0.47
     ski
    0.47
     intake
    0.46
    let
    0.46
    Activations Density 0.000%

    No Known Activations