© 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. 179486
    Prev
    Next
    INDEX
    Explanations

    legal documentation

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

    prevent sacrificing review context declare

    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
    襁
    0.52
     pulleys
    0.45
     אנ
    0.44
     handkerchief
    0.44
    Inde
    0.43
    秸
    0.43
    ,&
    0.43
    出自
    0.42
     بنی
    0.42
    ,=
    0.42
    POSITIVE LOGITS
    er
    0.56
    ag
    0.54
    il
    0.53
    ad
    0.51
     {
    0.51
    り
    0.51
    r
    0.50
    és
    0.49
    ut
    0.48
     brauch
    0.48
    Activations Density 0.001%

    No Known Activations