© 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. 37311
    Prev
    Next
    INDEX
    Explanations

    fromcourier deliveredcircle traditionwants to

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

    generating routines and instructions

    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
    res
    0.77
    ten
    0.74
    f
    0.73
    j
    0.67
    k
    0.66
    US
    0.64
    FL
    0.63
    en
    0.61
    v
    0.60
    c
    0.60
    POSITIVE LOGITS
     botón
    0.52
    ванный
    0.50
     routines
    0.49
     dezembro
    0.49
     adolescence
    0.49
     instances
    0.48
     mediocr
    0.47
     recipes
    0.47
     edição
    0.47
     সত্ত্বেও
    0.46
    Activations Density 0.000%

    No Known Activations