© 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. 135608
    Prev
    Next
    INDEX
    Explanations

    size up, vintage looking

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

    SEO keywords and structured information

    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
     customers
    0.49
    由
    0.47
     budd
    0.45
     Lach
    0.45
     verticals
    0.44
     data
    0.43
     product
    0.43
     pitches
    0.43
     relation
    0.43
     mortg
    0.43
    POSITIVE LOGITS
     اﻻ
    0.46
    bestand
    0.46
     來
    0.46
    asco
    0.43
     ー
    0.42
     requisito
    0.42
     liné
    0.42
     tivesse
    0.42
    สั่ง
    0.42
    thaus
    0.42
    Activations Density 0.000%

    No Known Activations