© 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. 209386
    Prev
    Next
    INDEX
    Explanations

    handling subsequent items

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

    softened to room temperature

    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
     полови
    0.49
    ugging
    0.46
     raping
    0.41
    africa
    0.41
    LetterGrade
    0.41
     independientes
    0.40
    })^{
    0.40
    Lk
    0.40
     indecent
    0.40
    apons
    0.40
    POSITIVE LOGITS
    座標
    0.46
     Since
    0.45
     dotyczące
    0.43
    শিল্প
    0.42
     tombe
    0.42
     nächste
    0.42
     زندہ
    0.41
     現
    0.41
     Modular
    0.41
     Stück
    0.40
    Activations Density 0.002%

    No Known Activations