© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11793
    Prev
    Next
    INDEX
    Explanations

    class constructors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subalgebras
    1.29
     жителей
    1.28
    Վ
    1.25
     údaje
    1.24
     Helmet
    1.23
    ️⃣
    1.22
    }));
    1.21
    ﻖ
    1.20
    LEADING
    1.19
     Normalmente
    1.19
    POSITIVE LOGITS
    みました
    1.46
    dag
    1.36
    ments
    1.36
    suits
    1.27
    side
    1.27
    но
    1.25
    ো
    1.21
    و
    1.18
     устра
    1.16
    d
    1.16
    Activations Density 0.001%

    No Known Activations