© 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. 182172
    Prev
    Next
    INDEX
    Explanations

    away from, portion of, party games

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

    completion phrases

    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
    ’
    0.45
    ↵
    0.43
    stm
    0.43
     ul
    0.42
     смогут
    0.41
    >>
    0.41
     uni
    0.41
    рисов
    0.41
     resul
    0.41
    enabled
    0.40
    POSITIVE LOGITS
    觐
    0.51
    kę
    0.51
     靴
    0.51
     पुरात
    0.50
    əd
    0.50
     tradizione
    0.49
    ະລ
    0.49
    趾
    0.49
    だと思います
    0.49
     गैस
    0.48
    Activations Density 0.000%

    No Known Activations