© 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. 25289
    Prev
    Next
    INDEX
    Explanations

    created by

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

    technical discovery or action

    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
    Fortune
    0.50
    Agg
    0.48
    犹如
    0.47
    Latitude
    0.46
    אי
    0.46
    Already
    0.45
    小区
    0.45
    Ї
    0.45
    Tiny
    0.45
    Всім
    0.45
    POSITIVE LOGITS
     ɔ
    0.47
     高級
    0.46
     amyl
    0.45
     vaccines
    0.45
     fluids
    0.45
     aerodynamics
    0.45
     dancer
    0.44
     DUT
    0.44
     constitution
    0.44
     中央
    0.44
    Activations Density 0.000%

    No Known Activations