© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104446
    Prev
    Next
    INDEX
    Explanations

    other forms or our customers

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

    debugging and technical setup

    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
    ן
    0.60
     clause
    0.50
    ottam
    0.48
    ipari
    0.46
     学
    0.45
     短
    0.45
     制
    0.45
     упраж
    0.45
     企业
    0.45
     法
    0.44
    POSITIVE LOGITS
     Smoothie
    0.45
     Complet
    0.44
     progr
    0.44
     komplet
    0.44
    림
    0.44
     chimie
    0.43
     Disrupt
    0.43
     reúne
    0.42
     Comando
    0.42
     Doktor
    0.42
    Activations Density 0.000%

    No Known Activations