© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58277
    Prev
    Next
    INDEX
    Explanations

    This fire, me what

    np_acts-logits-general · gemini-2.5-flash-lite

    Young followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trong
    0.46
     unquestion
    0.43
     antigüedad
    0.42
     dimensión
    0.41
    렐
    0.40
    gebied
    0.39
     menschen
    0.39
     műkö
    0.39
     foundational
    0.38
     Rise
    0.38
    POSITIVE LOGITS
    🎏
    0.48
    akas
    0.47
     चीन
    0.47
     cAMP
    0.47
     পাকিস্তানীরা
    0.46
     idempot
    0.46
     ಎರಡು
    0.46
     adsor
    0.46
     שני
    0.46
     இரண்டு
    0.45
    Activations Density 0.000%

    No Known Activations