© 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. 125968
    Prev
    Next
    INDEX
    Explanations

    download, for, ?, ., to, with, be

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

    independently or lacking certain qualities

    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
     여러분
    0.52
     sweetest
    0.48
     CommandCenter
    0.46
     軍
    0.46
     એવી
    0.46
     endeav
    0.45
     Oriente
    0.45
    rangea
    0.45
     فوجی
    0.45
    군의
    0.44
    POSITIVE LOGITS
    Lamp
    0.51
    燬
    0.51
     tabella
    0.49
    الات
    0.49
     réception
    0.48
     propriedade
    0.47
     vibration
    0.47
    Neue
    0.47
     lamp
    0.46
    品質
    0.46
    Activations Density 0.001%

    No Known Activations