© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 234064
    Prev
    Next
    INDEX
    Explanations

    king over

    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
     kadar
    0.45
    坩
    0.44
     kapas
    0.43
    蜱
    0.43
     özellikleri
    0.42
    ?”
    0.42
     bhfuil
    0.41
    鬣
    0.41
     описание
    0.41
     együtt
    0.41
    POSITIVE LOGITS
     worsening
    0.49
     deoarece
    0.48
     deteriorating
    0.46
    क्योंकि
    0.46
     ಇದರಿಂದ
    0.45
     причиной
    0.44
     retarded
    0.43
    ret
    0.43
     क्योंकि
    0.43
    oarece
    0.43
    Activations Density 0.002%

    No Known Activations