© 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. 228393
    Prev
    Next
    INDEX
    Explanations

    Again,

    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
    markt
    0.46
    toadd
    0.46
    eqn
    0.46
     ゴルフ
    0.45
    ('*
    0.45
    mtd
    0.45
    {
    0.44
    o
    0.44
    erat
    0.43
    t
    0.42
    POSITIVE LOGITS
    𒅆
    0.46
    »,
    0.46
     story
    0.45
     hebat
    0.45
     menjelaskan
    0.45
     sakit
    0.45
    ਤਾ
    0.45
    形势
    0.44
    蛩
    0.44
     berbeda
    0.43
    Activations Density 0.001%

    No Known Activations