© 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. 228501
    Prev
    Next
    INDEX
    Explanations

    certified options, above existing

    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
     defra
    0.51
     ลํา
    0.48
     információ
    0.47
     president
    0.46
    "):
    0.46
     circumfer
    0.46
    ْنَ
    0.46
     yere
    0.45
     měli
    0.45
     nuestros
    0.44
    POSITIVE LOGITS
    ཞ
    0.49
    บู
    0.47
    Crypt
    0.45
    Keyword
    0.44
    สา
    0.44
    Bounce
    0.44
    鐲
    0.44
    workItem
    0.44
     пласти
    0.43
    Де
    0.43
    Activations Density 0.000%

    No Known Activations