© 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-16K
    7. 1094
    Prev
    Next
    INDEX
    Explanations

    phrases describing concepts

    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_16k_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
    linear
    1.81
    𝐠
    1.78
    h
    1.76
    shovel
    1.74
    Siehe
    1.66
    o
    1.64
     coprime
    1.64
    an
    1.64
    𝐢
    1.60
    ggi
    1.60
    POSITIVE LOGITS
     وا
    1.68
    деся
    1.64
     warum
    1.64
     aspects
    1.60
    лега
    1.56
     zat
    1.55
    PACT
    1.54
     얼마나
    1.53
     rokov
    1.51
    𝗹
    1.51
    Activations Density 0.269%

    No Known Activations