© 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. 132451
    Prev
    Next
    INDEX
    Explanations

    family relationships

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

    common phrases and structures

    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
    icida
    0.54
     izinsuku
    0.53
    㞱
    0.51
     núcle
    0.51
     Methyl
    0.50
    ீரல்
    0.50
    ifères
    0.50
    ;</
    0.50
     лета
    0.50
    नीचर
    0.50
    POSITIVE LOGITS
    ৪
    0.45
    ارع
    0.43
    old
    0.43
    power
    0.42
     velocity
    0.41
     utilisation
    0.41
    電力
    0.40
     डील
    0.40
    မ်
    0.40
     prosecution
    0.39
    Activations Density 0.002%

    No Known Activations