© 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-65K
    7. 3160
    Prev
    Next
    INDEX
    Explanations

    adding and addition

    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_65k_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
    െന്നാണ്
    0.67
    FileAlignment
    0.66
    rž
    0.64
    ^{*}}{\
    0.62
    pegno
    0.62
     تیاری
    0.60
    entrale
    0.59
    魈
    0.59
    óz
    0.59
     যাবত
    0.57
    POSITIVE LOGITS
     add
    5.20
     adding
    5.10
     Add
    5.00
    Add
    4.98
     Adding
    4.97
     addition
    4.93
    Adding
    4.91
     added
    4.88
     adds
    4.81
    add
    4.76
    Activations Density 2.133%

    No Known Activations