© 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. 2204
    Prev
    Next
    INDEX
    Explanations

    numbered sections and arguments

    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
    nost
    0.69
    no
    0.64
     ult
    0.61
     raining
    0.59
     neither
    0.58
    ↵↵↵
    0.58
     frame
    0.55
     rain
    0.55
     common
    0.55
     k
    0.55
    POSITIVE LOGITS
    Ꭽ
    0.83
    gateTime
    0.81
     radionu
    0.80
     Paytm
    0.80
     акча
    0.78
     držav
    0.78
     palco
    0.78
     Испании
    0.78
    ificante
    0.76
    zellen
    0.76
    Activations Density 0.190%

    No Known Activations