© 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. 191535
    Prev
    Next
    INDEX
    Explanations

    year followed by punctuation or descriptive text

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

    subjective ability IQ price

    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
    িকপ্ট
    0.52
    ୍କ
    0.51
    ჲ
    0.50
    ឧ
    0.50
    輥
    0.48
    Haryana
    0.47
    ეტ
    0.47
     électrique
    0.47
    ąp
    0.46
     chandeliers
    0.46
    POSITIVE LOGITS
    不可
    0.48
    生活
    0.48
    <0xE3>
    0.47
    答
    0.45
     Isla
    0.45
    0.44
    做
    0.43
     massa
    0.43
    ，
    0.43
    去年
    0.42
    Activations Density 0.003%

    No Known Activations