© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 112187
    Prev
    Next
    INDEX
    Explanations

    download-only tales

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

    genetic changes

    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
     السابق
    0.47
    送
    0.47
    over
    0.45
    Exist
    0.44
     hebben
    0.43
    reek
    0.42
    坠
    0.42
     zitten
    0.42
    ကျ
    0.41
    Ờ
    0.41
    POSITIVE LOGITS
     finit
    0.52
     defens
    0.50
     путем
    0.50
     recoil
    0.48
     subter
    0.46
     específicamente
    0.46
    ífica
    0.45
    ioxide
    0.45
     militar
    0.44
     WPS
    0.44
    Activations Density 0.000%

    No Known Activations