© 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. 105229
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases and relationships

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

    list items or topics

    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
    łego
    0.52
    ⤠
    0.50
    żyt
    0.45
    殃
    0.44
    toBe
    0.44
    πουργ
    0.44
    伒
    0.44
    ಟ್
    0.43
    ınca
    0.43
    cych
    0.43
    POSITIVE LOGITS
     myopia
    0.47
     specialization
    0.44
     phenyl
    0.42
    KIT
    0.41
     flexibility
    0.41
     glitter
    0.41
     rendezvous
    0.41
     BONUS
    0.41
     aesthetics
    0.40
     TZ
    0.40
    Activations Density 0.000%

    No Known Activations