© 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. 5647
    Prev
    Next
    INDEX
    Explanations

    enumerating grandchildren

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

    subspecies and synonyms

    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
     подарок
    0.41
     døde
    0.40
    lysninger
    0.40
    公元
    0.39
    诽
    0.39
     গেছেন
    0.39
     родился
    0.38
     morreu
    0.38
     dniu
    0.37
     emple
    0.37
    POSITIVE LOGITS
    が集
    0.45
     total
    0.45
     variously
    0.43
     boomers
    0.43
     πολλ
    0.42
     totals
    0.42
     subgroups
    0.41
     SUBTOTAL
    0.40
    totals
    0.40
    :,
    0.39
    Activations Density 0.002%

    No Known Activations