© 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. 216617
    Prev
    Next
    INDEX
    Explanations

    links tofar fromvariations amongproducts usingquotation. Delivery

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

    less/without modifying

    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
    ।
    0.50
     moderation
    0.45
     E
    0.45
     pensa
    0.44
     I
    0.43
    🛳
    0.43
     perspective
    0.43
     appearing
    0.42
     (?
    0.42
     (-
    0.41
    POSITIVE LOGITS
    auh
    0.51
    ورك
    0.51
    حي
    0.49
    கரு
    0.47
    apel
    0.47
    ulik
    0.47
    instead
    0.47
    ikums
    0.46
    wärt
    0.46
     statt
    0.46
    Activations Density 0.000%

    No Known Activations