© 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. 181016
    Prev
    Next
    INDEX
    Explanations

    compatible, incorporated, Pro, clearance

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

    Panel breakdown and workflow

    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
     rezat
    0.50
    kiem
    0.49
    ма
    0.49
    craft
    0.48
    𝓪
    0.48
     allege
    0.48
    kuje
    0.47
     воздух
    0.47
     брат
    0.47
    াহিয়া
    0.47
    POSITIVE LOGITS
    戴
    0.46
    ☺
    0.42
    uggish
    0.42
     Smartphones
    0.42
    修理
    0.42
    世纪
    0.41
    并非
    0.40
    慈善
    0.40
    泼
    0.40
    亿
    0.39
    Activations Density 0.000%

    No Known Activations