© 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. 112300
    Prev
    Next
    INDEX
    Explanations

    `--option name` or `flag name`

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

    command-line arguments and descriptions

    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
     anticor
    0.44
     impuestos
    0.44
     yes
    0.43
     ∞
    0.43
     apiKey
    0.43
     bū
    0.42
     globales
    0.42
     order
    0.42
     http
    0.42
     autof
    0.42
    POSITIVE LOGITS
    🧁
    0.55
    ફ
    0.51
     بھول
    0.48
    이상
    0.47
    ヲ
    0.47
     кількість
    0.47
    եր
    0.46
    ഡ്
    0.46
     впли
    0.46
    靦
    0.46
    Activations Density 0.000%

    No Known Activations