© 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. 152282
    Prev
    Next
    INDEX
    Explanations

    trap and lock allergens

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

    basic recall and recognition

    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
     flamingo
    0.45
     θε
    0.44
     matematica
    0.44
     सफल
    0.44
    煨
    0.43
     подпис
    0.43
    ün
    0.42
     लिखी
    0.42
     क्रिया
    0.42
     생
    0.41
    POSITIVE LOGITS
    二人
    0.52
     accommodating
    0.48
    ્ષ
    0.47
    شك
    0.44
     trajectories
    0.44
    يارات
    0.44
    ดูก
    0.44
    jectories
    0.42
     Schritte
    0.42
    界面
    0.42
    Activations Density 0.000%

    No Known Activations