© 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. 189339
    Prev
    Next
    INDEX
    Explanations

    relationships with

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

    historical relationship, not entirely arbitrary

    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
    áln
    0.46
    かと思います
    0.45
     Summer
    0.45
    蔼
    0.43
     summer
    0.42
     SUMMER
    0.41
     Romney
    0.41
    airo
    0.41
    ulan
    0.40
     çal
    0.40
    POSITIVE LOGITS
     Tá
    0.47
    Გ
    0.47
    ডি
    0.46
     Productos
    0.45
    Ს
    0.44
    ').':
    0.42
     ಬಾ
    0.42
    towards
    0.42
     visualizar
    0.41
     conectar
    0.41
    Activations Density 0.001%

    No Known Activations