© 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. 115850
    Prev
    Next
    INDEX
    Explanations

    items, state, odors, orders

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

    institutions, concepts, and specific names

    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
    :",
    0.48
    ",
    0.47
    Iterable
    0.44
    ","/
    0.44
    s
    0.44
    dec
    0.44
    Thought
    0.43
    大切
    0.43
    Restrictions
    0.42
    That
    0.41
    POSITIVE LOGITS
     Shankar
    0.53
     ജില്ലാ
    0.50
     gestern
    0.49
    Ⴀ
    0.48
     Shastri
    0.48
     Špan
    0.47
     හොඳ
    0.46
     Sarkar
    0.46
     Srivastava
    0.46
    糍
    0.46
    Activations Density 0.002%

    No Known Activations