© 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. 70400
    Prev
    Next
    INDEX
    Explanations

    Discover past title facilities

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

    founder reserved

    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
     одному
    0.49
     arrondi
    0.49
     transitioned
    0.48
    のだ
    0.47
    觎
    0.46
     направлении
    0.46
    ч
    0.46
    ಿತ್ತು
    0.44
    一緒に
    0.44
     irritated
    0.44
    POSITIVE LOGITS
     permite
    0.60
     Doct
    0.54
     dox
    0.52
    ळी
    0.52
     do
    0.51
    3
    0.51
     p
    0.51
     Mer
    0.51
     Ash
    0.51
     hinge
    0.50
    Activations Density 0.000%

    No Known Activations