© 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. 174283
    Prev
    Next
    INDEX
    Explanations

    website, securely, importantly

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

    structural or conceptual parts

    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
    čky
    0.59
    féle
    0.50
     Entwick
    0.50
     Australie
    0.49
    䝬
    0.49
    ంట
    0.49
     लड़
    0.48
    Été
    0.48
     vždy
    0.47
    ísim
    0.47
    POSITIVE LOGITS
     conceptual
    0.51
     transaction
    0.51
    MAR
    0.48
    Б
    0.48
     specifics
    0.48
     sponsorship
    0.47
    USION
    0.47
     component
    0.46
     specific
    0.46
    component
    0.46
    Activations Density 0.002%

    No Known Activations