© 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. 98569
    Prev
    Next
    INDEX
    Explanations

    new terms and phrases

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

    limits access

    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
     fishes
    0.47
     ､
    0.44
     idling
    0.43
    电压
    0.43
    ایات
    0.43
     管
    0.42
     pinching
    0.42
     voltages
    0.41
     travail
    0.41
    ต่ำ
    0.41
    POSITIVE LOGITS
     nieuwe
    0.45
     ново
    0.45
    的新
    0.45
     nuova
    0.44
    𝙜
    0.44
    jdk
    0.44
     नवे
    0.43
    area
    0.42
    బాటు
    0.42
    apod
    0.42
    Activations Density 0.000%

    No Known Activations