© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3793
    Prev
    Next
    INDEX
    Explanations

    anime waifus

    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
    <unused2117>
    1.17
    <unused2123>
    1.15
     yahoo
    1.09
     TPM
    1.09
     SRM
    1.08
     mickey
    1.07
     Trento
    1.07
     ADS
    1.07
     CIN
    1.06
    <unused2109>
    1.05
    POSITIVE LOGITS
    Sw
    1.04
     ప్ర
    0.92
     Em
    0.91
     Ver
    0.90
     Sw
    0.90
     Pe
    0.90
     Met
    0.88
     Sch
    0.86
    Sch
    0.85
     Mel
    0.84
    Activations Density 1.006%

    No Known Activations