© 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. 229085
    Prev
    Next
    INDEX
    Explanations

    to be confirmed

    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
     uniqueness
    0.58
     neckline
    0.54
     adenosine
    0.52
     anillo
    0.50
    )
    0.50
     acetylcholine
    0.50
     plasmid
    0.48
     flight
    0.47
     pathway
    0.47
     stenosis
    0.47
    POSITIVE LOGITS
    一般的な
    0.56
    Fernseh
    0.55
     സര്‍ക്കാര്‍
    0.54
     पॉलिटी
    0.53
     Poland
    0.51
     Bereiche
    0.51
     ضمن
    0.50
    훈
    0.50
     போலீசார்
    0.49
     බොහෝ
    0.49
    Activations Density 0.002%

    No Known Activations