© 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. 58414
    Prev
    Next
    INDEX
    Explanations

    . Remember. Howeveron wherea manthese crimes

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

    complete overhaul

    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
     газо
    0.52
    劑
    0.51
     ультра
    0.50
     осмо
    0.50
     уско
    0.48
     жителей
    0.47
     إلي
    0.46
     فى
    0.46
     играет
    0.46
     מפ
    0.46
    POSITIVE LOGITS
    r
    0.50
    n
    0.45
    -
    0.44
     cryptographic
    0.44
     bearer
    0.42
    屋内
    0.42
     Management
    0.41
    ٹا
    0.41
    al
    0.40
    نما
    0.40
    Activations Density 0.000%

    No Known Activations