© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 145430
    Prev
    Next
    INDEX
    Explanations

    paid tutors

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <unused408>
    0.85
     ligação
    0.83
    ಾಸ
    0.80
     forças
    0.79
    <unused1102>
    0.78
    бор
    0.77
     sebum
    0.77
    ススメ
    0.77
     bombé
    0.77
    <unused761>
    0.76
    POSITIVE LOGITS
     blind
    0.63
    anyu
    0.61
     Bi
    0.60
     ur
    0.60
     located
    0.58
    /.
    0.56
     res
    0.56
    resi
    0.55
    Bi
    0.55
    ㅡ
    0.55
    Activations Density 0.001%

    No Known Activations