© 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. 40210
    Prev
    Next
    INDEX
    Explanations

    descriptions, technique, defense, filter

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

    technical terms and abbreviations

    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
    και
    0.64
    and
    0.58
    analysis
    0.57
     και
    0.55
    analisi
    0.54
    และ
    0.53
     и
    0.53
    и
    0.53
     וב
    0.52
    và
    0.52
    POSITIVE LOGITS
     anthocyan
    0.48
     Lebensmittel
    0.46
     lehetős
    0.45
     Mavic
    0.44
     mAh
    0.43
     übrig
    0.43
     legger
    0.43
     Gnome
    0.43
     možnost
    0.42
     certains
    0.42
    Activations Density 0.000%

    No Known Activations