© 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. 223593
    Prev
    Next
    INDEX
    Explanations

    long are, often have

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

    elevated compared to

    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
    b
    0.62
    да
    0.54
    r
    0.52
    たん
    0.50
    d
    0.49
    c
    0.49
    х
    0.48
    \|
    0.47
    n
    0.47
     ANC
    0.47
    POSITIVE LOGITS
     माफी
    0.56
     allError
    0.52
     отношение
    0.51
     muros
    0.51
     வண்ணப்பூச்சு
    0.50
     centros
    0.49
     విధంగా
    0.49
     המת
    0.48
    pkins
    0.47
     बनी
    0.47
    Activations Density 0.000%

    No Known Activations