© 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. 91603
    Prev
    Next
    INDEX
    Explanations

    ordered; making sure

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

    comforting sensations and ease

    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
     förb
    0.48
    CDATA
    0.45
    UTF
    0.45
    CT
    0.44
    ORM
    0.44
    篂
    0.44
     Guang
    0.43
    ACI
    0.43
    弄
    0.43
    UC
    0.42
    POSITIVE LOGITS
     metaverse
    0.53
     sacchar
    0.50
     boissons
    0.46
    opause
    0.46
     ⭐
    0.46
     chaleur
    0.45
    เนื้อ
    0.45
     ✨
    0.45
     हीट
    0.45
    нії
    0.44
    Activations Density 0.001%

    No Known Activations