© 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. 29636
    Prev
    Next
    INDEX
    Explanations

    comments and trackbacks closed

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

    binary and non-binary terms

    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
    드를
    0.50
    зло
    0.48
    AGG
    0.46
    fix
    0.44
    ιση
    0.44
    뜬
    0.43
    盯着
    0.43
    बिन
    0.42
    掉
    0.42
    ఫ్‌
    0.42
    POSITIVE LOGITS
    ný
    0.55
    絟
    0.54
     clientèle
    0.46
     osztály
    0.46
     relat
    0.46
     محاضرات
    0.45
    خواه
    0.45
     рабочий
    0.45
    賏
    0.44
    рі
    0.43
    Activations Density 0.000%

    No Known Activations