© 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. 91245
    Prev
    Next
    INDEX
    Explanations

    program strategy

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

    diagnosis, data, specifying

    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
     McClure
    0.45
    નગર
    0.44
    вело
    0.42
     McM
    0.42
     McDaniel
    0.42
     అధికారులు
    0.40
     Audubon
    0.40
    🟢
    0.40
    外界
    0.39
    thorpe
    0.39
    POSITIVE LOGITS
     زیبا
    0.49
    𝓼
    0.46
     زیبایی
    0.45
     मर्या
    0.43
    ofil
    0.43
    ہیں
    0.42
     lengan
    0.42
     সুন্দরী
    0.42
     düzen
    0.41
     نوٹ
    0.41
    Activations Density 0.000%

    No Known Activations