© 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. 58328
    Prev
    Next
    INDEX
    Explanations

    "is not" or "is either"

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

    seasonal vegetables, understand timing

    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
     брать
    0.45
     いた
    0.44
    র
    0.44
     구축
    0.43
     lymphoma
    0.41
     izgrad
    0.41
     fecund
    0.40
     осуществляется
    0.40
     đều
    0.40
     destruir
    0.40
    POSITIVE LOGITS
    岃
    0.49
    ical
    0.46
    itle
    0.45
     Thankfully
    0.44
    住所
    0.44
     Detalles
    0.44
    और
    0.43
    തിൽ
    0.42
    ingly
    0.42
     लोगो
    0.41
    Activations Density 0.000%

    No Known Activations