© 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. 3246
    Prev
    Next
    INDEX
    Explanations

    listing options

    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
    ťou
    0.71
    citet
    0.70
    existing
    0.70
    straight
    0.70
    <0xD8>
    0.68
    substantial
    0.66
    exactly
    0.65
    sometimes
    0.65
    nullptr
    0.65
    في
    0.64
    POSITIVE LOGITS
     III
    1.39
     #
    1.24
     IV
    1.17
     II
    1.13
    ＃
    1.12
     Nummer
    1.11
     VII
    1.09
     VIII
    1.07
     Nr
    1.04
     nummer
    1.04
    Activations Density 0.412%

    No Known Activations