© 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. 49992
    Prev
    Next
    INDEX
    Explanations

    but for

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

    game of thrones ending

    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
     or
    0.44
    /
    0.44
     cierre
    0.42
    知道了
    0.41
     ismer
    0.41
    ों
    0.41
    Gap
    0.41
     \'
    0.40
     arena
    0.40
    ים
    0.40
    POSITIVE LOGITS
    ᴙ
    0.51
    glicherweise
    0.50
     Gorg
    0.46
    GRAND
    0.46
     oscilloscope
    0.45
    
    0.44
     raisons
    0.43
    酵素
    0.43
     grandiose
    0.43
    artan
    0.42
    Activations Density 0.000%

    No Known Activations