© 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. 145691
    Prev
    Next
    INDEX
    Explanations

    safe and helpful

    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
    alea
    0.77
    ।-
    0.76
     GATE
    0.73
     দয়া
    0.69
     জৈন
    0.69
    بیل
    0.68
    仡
    0.68
    诰
    0.68
     만드는
    0.68
    ającej
    0.67
    POSITIVE LOGITS
     Sound
    0.92
     seclusion
    0.89
     soundness
    0.87
     sound
    0.86
    sound
    0.85
    Sound
    0.84
     efficacy
    0.80
     secure
    0.79
    Secure
    0.78
     security
    0.76
    Activations Density 0.017%

    No Known Activations