© 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. 240328
    Prev
    Next
    INDEX
    Explanations

    Aspen Colorado podcast studying tools

    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
     majorité
    0.43
    痘
    0.41
     exacerbated
    0.41
     aperto
    0.41
    COMPAR
    0.41
     succumbed
    0.41
    FUNCION
    0.40
     Affairs
    0.40
    olon
    0.40
    ेने
    0.40
    POSITIVE LOGITS
    ງ
    0.48
    ယ
    0.47
    ად
    0.44
    Angleterre
    0.43
     advices
    0.43
    iami
    0.43
     commissions
    0.42
     ng
    0.42
    SKA
    0.40
     advice
    0.39
    Activations Density 0.006%

    No Known Activations