© 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. 21965
    Prev
    Next
    INDEX
    Explanations

    Specific names/titles followed by context

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

    regulation, biodiversity, conservation

    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
    ktion
    0.47
    ucapkan
    0.47
    णाम
    0.46
    Tempor
    0.44
    ીએ
    0.43
     रिली
    0.43
    ounsel
    0.42
    ̖
    0.42
    PatientR
    0.42
    uyên
    0.42
    POSITIVE LOGITS
     Pretoria
    0.49
     barter
    0.46
     wetlands
    0.45
     Gippsland
    0.45
     one
    0.44
     symmetrically
    0.43
     nought
    0.43
     wetland
    0.43
     enclose
    0.42
     Croydon
    0.42
    Activations Density 0.000%

    No Known Activations