© 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. 3507
    Prev
    Next
    INDEX
    Explanations

    Names starting with Sil, Hor, Cy, Crist, Arist

    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
     JSON
    0.69
     Creation
    0.69
     XRD
    0.65
     miRNA
    0.61
    ㅏ
    0.61
    Sprint
    0.60
     Create
    0.60
     👀
    0.59
     NSA
    0.59
     Dhoni
    0.59
    POSITIVE LOGITS
    ibald
    1.40
    ianus
    1.40
    asius
    1.37
    ucius
    1.34
    udius
    1.25
    ilius
    1.23
    odore
    1.19
    berto
    1.18
    inius
    1.18
    fried
    1.17
    Activations Density 0.051%

    No Known Activations