© 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. 16-GEMMASCOPE-2-RES-16K
    7. 453
    Prev
    Next
    INDEX
    Explanations

    discussion degrees

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

    export var, coming from, powerful asset

    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_16_width_16k_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
    א
    0.64
    ק
    0.64
    י
    0.63
    צ
    0.63
    および
    0.60
    אן
    0.60
    ้ง
    0.59
    ก
    0.59
    ığı
    0.58
    󠁳
    0.58
    POSITIVE LOGITS
    y
    0.68
    al
    0.56
    o
    0.55
    t
    0.52
    cout
    0.51
     borders
    0.51
     svart
    0.51
    pres
    0.50
    genes
    0.50
    travel
    0.50
    Activations Density 0.002%

    No Known Activations