© 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. 200445
    Prev
    Next
    INDEX
    Explanations

    items, categories, places

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

    mode decomposition verify check vary deleted

    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
    ת
    0.56
    2
    0.54
    ing
    0.52
    (
    0.50
    א
    0.49
    同士
    0.48
     things
    0.47
     —
    0.47
    s
    0.46
    r
    0.45
    POSITIVE LOGITS
     நீதி
    0.52
     તરીકે
    0.50
     закона
    0.49
     sifatida
    0.49
     agacch
    0.47
     veditabbo
    0.47
    వంటి
    0.47
    ബരി
    0.46
     vuccati
    0.46
    čen
    0.46
    Activations Density 0.002%

    No Known Activations