© 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. 150617
    Prev
    Next
    INDEX
    Explanations

    save cash

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

    ultimately, navigating, social, control

    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
     recta
    0.49
     competencia
    0.48
     سنا
    0.47
    лле
    0.46
    aturas
    0.45
     inmediata
    0.45
     expectant
    0.44
     ဗ
    0.44
     conciencia
    0.44
     pretensions
    0.44
    POSITIVE LOGITS
    תר
    0.45
     widths
    0.45
     nemá
    0.44
    קי
    0.44
    ný
    0.43
    繡
    0.43
    lığ
    0.43
    กัน
    0.43
    屐
    0.43
     gehörte
    0.42
    Activations Density 0.000%

    No Known Activations