© 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. 69052
    Prev
    Next
    INDEX
    Explanations

    utilized in

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

    will not suggest

    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
    тность
    0.57
    ves
    0.54
    ativa
    0.51
     រ
    0.51
    ustom
    0.48
    ał
    0.47
    hoot
    0.47
     интересный
    0.47
    atio
    0.46
     výraz
    0.46
    POSITIVE LOGITS
     everytime
    0.49
    しっかり
    0.46
    ここに
    0.44
     TODOS
    0.44
    ίζ
    0.42
    😪
    0.41
    無い
    0.41
     sooo
    0.40
     pedi
    0.40
    まで
    0.40
    Activations Density 0.001%

    No Known Activations