© 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. 112562
    Prev
    Next
    INDEX
    Explanations

    personal information and questions

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

    strengths and weaknesses

    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
    č
    0.50
     renters
    0.49
    opi
    0.47
     rescuers
    0.46
    ab
    0.46
    ientôt
    0.46
     sprouted
    0.45
    newMessage
    0.45
     bé
    0.44
    itis
    0.44
    POSITIVE LOGITS
     dismissal
    0.47
     imidazole
    0.45
     PERSONAL
    0.45
     Авто
    0.44
     ব্যক্তিগত
    0.44
    ╿
    0.43
     VISIT
    0.43
     achievements
    0.43
     Engineer
    0.43
     форм
    0.42
    Activations Density 0.001%

    No Known Activations