© 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. 248621
    Prev
    Next
    INDEX
    Explanations

    narrative essay

    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
    ído
    0.60
     worden
    0.56
    ikova
    0.55
    ída
    0.52
    mrow
    0.50
    zaam
    0.50
     معك
    0.50
    í
    0.49
    uma
    0.49
     které
    0.48
    POSITIVE LOGITS
     BOOKS
    0.53
     Gifts
    0.52
     Memorial
    0.49
     TOOLS
    0.48
     Magistrates
    0.48
     Anthology
    0.48
     Picture
    0.47
     Bless
    0.47
     ITS
    0.47
     Emirates
    0.47
    Activations Density 0.001%

    No Known Activations