© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12257
    Prev
    Next
    INDEX
    Explanations

    form, file, Vapor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     वही
    1.76
    া
    1.69
    முத
    1.63
    flower
    1.53
    נו
    1.53
    ფილი
    1.50
    ة
    1.46
    ED
    1.45
    ed
    1.44
     ins
    1.44
    POSITIVE LOGITS
    ્સ
    2.41
    encer
    2.38
    𝗼
    2.36
    ャ
    2.17
    蜴
    2.16
    দের
    2.15
     comprensión
    2.14
    enced
    2.13
     allongé
    2.12
     détaillé
    2.12
    Activations Density 0.038%

    No Known Activations