© 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. 189967
    Prev
    Next
    INDEX
    Explanations

    discuss this

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

    exploring

    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
    军
    0.47
    要
    0.46
    พอ
    0.45
    าร
    0.45
    cuando
    0.45
    她
    0.44
    洲
    0.44
    游戏
    0.44
     ভাষা
    0.44
    Pokud
    0.43
    POSITIVE LOGITS
     +
    0.52
     positiva
    0.45
    +')
    0.45
     employing
    0.44
     tâm
    0.44
     Confidential
    0.44
     $+\
    0.44
     Confederation
    0.43
     اضافہ
    0.43
     +=
    0.43
    Activations Density 0.001%

    No Known Activations