© 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. 233140
    Prev
    Next
    INDEX
    Explanations

    secret versions

    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
    neapolis
    0.44
    搏
    0.43
     Collision
    0.42
    Ა
    0.42
    adah
    0.42
    ciation
    0.41
     Joints
    0.41
     Campus
    0.41
    EEEE
    0.41
     Physiological
    0.41
    POSITIVE LOGITS
    та
    0.67
    у
    0.57
     добав
    0.55
     perkara
    0.55
    про
    0.54
    ט
    0.54
     formação
    0.53
     ön
    0.51
    ată
    0.49
    тре
    0.49
    Activations Density 0.000%

    No Known Activations