© 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. 68787
    Prev
    Next
    INDEX
    Explanations

    followed through

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

    sellers, more, crucial, accurate, opportunities, purification

    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
    🐭
    0.47
    γε
    0.46
    нал
    0.45
    ຟ
    0.45
    峤
    0.45
    📅
    0.44
    꿩
    0.44
    ély
    0.44
    🗓
    0.44
     Mannschaften
    0.43
    POSITIVE LOGITS
    ి
    0.49
     rudder
    0.48
     ene
    0.46
    inari
    0.45
     course
    0.44
     neste
    0.44
     trav
    0.44
    ţi
    0.43
     guideline
    0.43
     tertiary
    0.43
    Activations Density 0.000%

    No Known Activations