© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2789
    Prev
    Next
    INDEX
    Explanations

    practical blueprint

    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_29_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
    :
    1.55
     initial
    0.99
     :-
    0.99
     extremely
    0.98
     generally
    0.97
     reputable
    0.95
     :
    0.94
     suitable
    0.94
     proper
    0.93
     correctly
    0.92
    POSITIVE LOGITS
    <unused1083>
    1.34
     Yardım
    1.31
    <unused1852>
    1.31
    <unused717>
    1.30
    <unused1096>
    1.30
     Nasıl
    1.23
    <unused1805>
    1.22
    <unused683>
    1.22
    牷
    1.22
    ítja
    1.21
    Activations Density 0.042%

    No Known Activations