© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5089
    Prev
    Next
    INDEX
    Explanations

    Basque, Spanish, Aragón

    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
     Sich
    0.70
     یق
    0.70
    ्रु
    0.67
     रॉ
    0.67
     қ
    0.66
     underscores
    0.65
     каб
    0.63
     madness
    0.61
     trouva
    0.61
    ㄑ
    0.61
    POSITIVE LOGITS
     haue
    1.10
     eta
    1.09
     edo
    1.09
     guzt
    1.07
     tx
    1.05
    Tx
    1.05
     erre
    1.03
    atuak
    1.03
     azalt
    0.97
     erab
    0.96
    Activations Density 0.043%

    No Known Activations