© 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. 65442
    Prev
    Next
    INDEX
    Explanations

    quotation followed by a word

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

    morning/afternoon greetings

    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
     сильно
    0.47
     छो
    0.47
     animación
    0.46
    chiha
    0.45
     pags
    0.45
    ➩
    0.45
     বৃত্তি
    0.45
     письма
    0.42
    赓
    0.42
    疤
    0.42
    POSITIVE LOGITS
     Veterin
    0.47
    ಂಟು
    0.44
     ヘッド
    0.43
     delighted
    0.43
    SET
    0.42
    aler
    0.42
     Anyone
    0.42
    専門
    0.42
     varieties
    0.42
    ראש
    0.42
    Activations Density 0.000%

    No Known Activations