© 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. 166235
    Prev
    Next
    INDEX
    Explanations

    start, problem, movers, Airlines

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

    session, Recession, initial, caller

    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
    cita
    0.45
    გი
    0.45
    ាន
    0.44
    dotto
    0.44
     Quindi
    0.44
    いち
    0.43
    \"");
    0.43
    ้ย
    0.43
    renderer
    0.42
    מי
    0.42
    POSITIVE LOGITS
     requête
    0.48
     başladı
    0.45
     pollut
    0.44
     bolster
    0.43
     révol
    0.42
    者
    0.42
    两
    0.42
     sagittal
    0.42
     baffle
    0.42
     hormonal
    0.41
    Activations Density 0.001%

    No Known Activations