© 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. 22475
    Prev
    Next
    INDEX
    Explanations

    Think back

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

    positive and negation

    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
     gmin
    0.45
    startTimestamp
    0.44
    슝
    0.43
    js
    0.42
    n
    0.42
    ໑
    0.41
    شي
    0.40
    А
    0.40
    فيد
    0.40
    шер
    0.40
    POSITIVE LOGITS
    larının
    0.53
     パンツ
    0.50
     마무리
    0.50
    <unused376>
    0.49
    <unused1004>
    0.48
     strengthening
    0.48
     付き
    0.48
     aik
    0.47
     மில்லியன்
    0.47
    )[
    0.46
    Activations Density 0.000%

    No Known Activations