© 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. 23667
    Prev
    Next
    INDEX
    Explanations

    much more

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

    preparation andsafety measures

    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
     Endocrinology
    0.55
     EGA
    0.54
     NaCl
    0.53
     Первая
    0.53
     ключ
    0.53
     Jugendliche
    0.52
     версия
    0.50
    闶
    0.49
     Функ
    0.49
     Президента
    0.49
    POSITIVE LOGITS
     Satin
    0.46
    igated
    0.42
     colaborador
    0.42
     donning
    0.41
    ﺬ
    0.41
    operatorname
    0.40
    댄
    0.40
    ﺪ
    0.40
    owner
    0.40
     scintillation
    0.39
    Activations Density 0.000%

    No Known Activations