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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 98956
    Prev
    Next
    INDEX
    Explanations

    youngest child

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     yle
    0.37
     ආහාර
    0.36
    Spell
    0.34
    Hidden
    0.34
     chodzi
    0.34
     sfondo
    0.34
    ˌ
    0.34
    ＰＥ
    0.34
     setzen
    0.33
    ㇂
    0.33
    POSITIVE LOGITS
    匚
    0.43
     ০
    0.39
    ائو
    0.38
    ल्
    0.38
     technologically
    0.37
     μας
    0.36
     প্রযুক্তি
    0.36
     Daphne
    0.35
    Robin
    0.35
    ificantly
    0.35
    Activations Density 0.002%

    No Known Activations