© 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. 137455
    Prev
    Next
    INDEX
    Explanations

    singles in

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

    glass membrane

    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
     দূরের
    0.58
    INTa
    0.54
     ভবিষ্যত
    0.54
    ᱽ
    0.54
    ‌ی
    0.52
    アクション
    0.52
    の新
    0.52
    の値
    0.52
     የማይ
    0.51
     ሕ
    0.50
    POSITIVE LOGITS
     doigts
    0.48
    رف
    0.43
    styles
    0.41
     deres
    0.40
    unix
    0.40
    ures
    0.40
    ré
    0.40
    }}(
    0.40
    roz
    0.40
    thesis
    0.40
    Activations Density 0.000%

    No Known Activations