© 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. 15354
    Prev
    Next
    INDEX
    Explanations

    Muertos, into the

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

    items and lists

    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
     بٹ
    0.47
    дравствуйте
    0.46
    墘
    0.45
    峤
    0.44
    Clamp
    0.44
    Onset
    0.43
    Truman
    0.42
    祯
    0.42
    玠
    0.42
    Tere
    0.42
    POSITIVE LOGITS
     próxima
    0.46
     pensions
    0.44
     algebras
    0.44
     ideia
    0.42
     capitalism
    0.42
     envisaged
    0.42
     festive
    0.42
     ideias
    0.41
     subtropical
    0.41
     autonomia
    0.41
    Activations Density 0.000%

    No Known Activations