© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 144494
    Prev
    Next
    INDEX
    Explanations

    injury, medication, death, or reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interchanges
    0.48
    گ
    0.48
     सकता
    0.47
     گیا
    0.45
     intercamb
    0.43
    ยาว
    0.43
    _$
    0.43
    Compra
    0.43
    %!
    0.43
     заменить
    0.42
    POSITIVE LOGITS
    ங்கிணை
    0.49
    vi
    0.47
     rám
    0.45
     hú
    0.45
    évén
    0.45
     endot
    0.44
    attended
    0.44
    uin
    0.44
    eti
    0.44
    äte
    0.44
    Activations Density 0.001%

    No Known Activations