© 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. 163197
    Prev
    Next
    INDEX
    Explanations

    organ, students, future, partnerships

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

    Identifying diseases and network beginners

    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
     சார
    0.54
    スイーツ
    0.53
     velocidade
    0.50
    ﺠ
    0.49
     कठोर
    0.48
     લગાવ
    0.48
     coração
    0.48
    utilisateur
    0.47
     cuore
    0.47
     verificación
    0.47
    POSITIVE LOGITS
    цтва
    0.52
     cunt
    0.50
     paradigms
    0.48
     binders
    0.47
     I
    0.47
     Barnard
    0.46
     flat
    0.45
    ados
    0.45
    鉉
    0.45
    తి
    0.45
    Activations Density 0.001%

    No Known Activations