© 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. 65139
    Prev
    Next
    INDEX
    Explanations

    your wedding, travel, child, Them

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

    facing outwards, fat or

    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
     उपलब्
    0.54
    ၿ
    0.51
    馊
    0.50
     powerplant
    0.50
     augmentation
    0.47
     gói
    0.47
     redução
    0.47
     chauffage
    0.47
    kangaroo
    0.46
     ቤት
    0.46
    POSITIVE LOGITS
    as
    0.52
    it
    0.49
    S
    0.48
    જા
    0.44
     it
    0.43
    It
    0.43
    ਜ
    0.43
    ActionBar
    0.42
    to
    0.41
     happened
    0.41
    Activations Density 0.000%

    No Known Activations