© 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. 3215
    Prev
    Next
    INDEX
    Explanations

    starting with "ab" or "ac"

    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
     シェ
    0.74
    še
    0.72
     Ше
    0.71
     Sho
    0.67
     লিল
    0.66
    ši
    0.66
     lượt
    0.66
    搅
    0.66
    ilyl
    0.64
    对称
    0.64
    POSITIVE LOGITS
    absolute
    0.71
     acc
    0.67
     abut
    0.67
     Absolute
    0.67
     conf
    0.66
     contraction
    0.66
     abatement
    0.65
    CTION
    0.65
     absolute
    0.65
     அப்ப
    0.64
    Activations Density 0.184%

    No Known Activations