© 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. 45110
    Prev
    Next
    INDEX
    Explanations

    Finnish local write have ask

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

    extinct, nearly extinct

    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
     ৪৮
    0.46
    étera
    0.45
    けて
    0.43
     compléter
    0.43
     comple
    0.43
     питания
    0.43
    కి
    0.42
     ±
    0.42
     यून
    0.42
     તરી
    0.42
    POSITIVE LOGITS
    ikat
    0.48
     ikat
    0.48
    rho
    0.45
    Hval
    0.45
     Gut
    0.45
    ک
    0.45
     Croatia
    0.44
    boldsymbol
    0.44
    plant
    0.44
     Alb
    0.44
    Activations Density 0.000%

    No Known Activations