© 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. 3756
    Prev
    Next
    INDEX
    Explanations

    languages and scripts

    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
    எ
    0.57
    ook
    0.53
    ired
    0.52
    oun
    0.52
     nak
    0.51
    idding
    0.51
    ουμε
    0.49
    ited
    0.49
    igated
    0.49
     q
    0.49
    POSITIVE LOGITS
     Hydraul
    0.76
     Comissão
    0.76
     ماشینونو
    0.76
     Đến
    0.76
     Clínica
    0.75
    Cantidad
    0.75
     Consejo
    0.74
     Akademii
    0.73
    También
    0.73
    Ejercicio
    0.72
    Activations Density 0.034%

    No Known Activations