© 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. 161425
    Prev
    Next
    INDEX
    Explanations

    operative constructions

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

    `.rs` file extension

    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
    volt
    0.44
    viel
    0.44
    vindos
    0.44
    rho
    0.42
    
    0.42
     đa
    0.41
     داشتن
    0.41
     orthogon
    0.41
    brainer
    0.40
     Bxe
    0.40
    POSITIVE LOGITS
    یدی
    0.51
    ודי
    0.48
    ი
    0.47
     operazioni
    0.46
    Operations
    0.46
    UIActions
    0.46
    بیر
    0.45
    ひとり
    0.45
    ाइ
    0.45
    Conse
    0.45
    Activations Density 0.000%

    No Known Activations