© 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. 145665
    Prev
    Next
    INDEX
    Explanations

    attached is or are

    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
    Not in Any Lists

    No Comments

    Negative Logits
     nakon
    0.85
    АС
    0.73
     κατο
    0.71
    ்
    0.70
     kanal
    0.70
     şek
    0.70
     पोस्टम
    0.69
     communaut
    0.69
     Wied
    0.68
    賢
    0.67
    POSITIVE LOGITS
     DOCUMENTS
    0.86
    are
    0.81
     Files
    0.79
     Are
    0.78
     are
    0.77
     Surveys
    0.77
    ambi
    0.77
     ARE
    0.77
     കൊണ്ട്
    0.76
     matching
    0.76
    Activations Density 0.000%

    No Known Activations