© 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-65K
    7. 2026
    Prev
    Next
    INDEX
    Explanations

    phrases starting with prepositions or auxiliary verbs

    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
    Negative Logits
    льти
    0.70
     imposed
    0.64
    decre
    0.63
    ónicos
    0.63
     буенча
    0.62
     Pawar
    0.62
    ಳಿ
    0.61
    ẋ
    0.61
     Almond
    0.59
    ือด
    0.58
    POSITIVE LOGITS
     anyone
    0.71
    ज़ाइन
    0.70
     concealment
    0.69
     তাৎ
    0.67
    er
    0.66
     detalhes
    0.64
    nehm
    0.64
     anybody
    0.63
    รายละเอียด
    0.63
    aino
    0.63
    Activations Density 0.000%

    No Known Activations