© 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. 248888
    Prev
    Next
    INDEX
    Explanations

    titles and performers

    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
     большинство
    0.46
    쥔
    0.45
     możesz
    0.45
     म्हणाले
    0.42
     mencionó
    0.41
     जितना
    0.41
    รอ
    0.41
    鄰
    0.41
    าน
    0.41
    िप्स
    0.40
    POSITIVE LOGITS
    raim
    0.52
    ari
    0.49
    etext
    0.49
    orah
    0.47
    elh
    0.47
    ilin
    0.46
    etric
    0.46
    yth
    0.46
    ovalent
    0.46
    auti
    0.46
    Activations Density 0.001%

    No Known Activations