© 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. 165782
    Prev
    Next
    INDEX
    Explanations

    image according

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

    easily or readily

    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
    ᕼ
    0.46
     {:?}",
    0.43
    ᱼ
    0.43
    ＿
    0.42
    "，
    0.42
    勅
    0.41
    邸
    0.41
    助
    0.41
    ваи
    0.41
    鳴
    0.41
    POSITIVE LOGITS
     qualsiasi
    0.51
     humanidad
    0.50
     qualquer
    0.45
     réellement
    0.45
     Effort
    0.44
     Femin
    0.44
     incompar
    0.44
     injustice
    0.43
     Tears
    0.43
     இறைவன்
    0.43
    Activations Density 0.001%

    No Known Activations