© 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. 218989
    Prev
    Next
    INDEX
    Explanations

    ordering or making choices

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

    ex machina

    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
     शतरंज
    0.48
    oeuvre
    0.45
    蠢
    0.45
     errone
    0.44
    isini
    0.44
    isinin
    0.44
     abiert
    0.44
     Croatian
    0.44
     unauthorised
    0.44
     शिवसेने
    0.44
    POSITIVE LOGITS
     ポリエステル
    0.49
     ジャケット
    0.47
     eman
    0.47
     angepasst
    0.46
     ingred
    0.42
     耐
    0.42
    FormParams
    0.42
     reinterpret
    0.42
     розподі
    0.41
     使っ
    0.41
    Activations Density 0.003%

    No Known Activations