© 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. 204697
    Prev
    Next
    INDEX
    Explanations

    type of

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

    repairing or specific terms

    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
    해가
    0.48
    3
    0.43
     YEARS
    0.42
    Quelle
    0.41
    Lens
    0.41
    года
    0.40
    বর্ষ
    0.40
    leaflet
    0.40
     Lest
    0.39
    *
    0.39
    POSITIVE LOGITS
    स्टम
    0.53
    นิยม
    0.53
     isomer
    0.52
     licensure
    0.51
     принято
    0.50
     aniline
    0.49
    NIH
    0.48
    alakip
    0.48
     denominada
    0.48
     ciphertext
    0.47
    Activations Density 0.000%

    No Known Activations