© 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. 111900
    Prev
    Next
    INDEX
    Explanations

    quality control

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

    ethical concerns

    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
    Inicial
    0.49
     Theoretically
    0.48
     যতক্ষণ
    0.46
    сної
    0.46
    algia
    0.45
    azion
    0.44
    🏬
    0.44
    Situ
    0.43
    sächlich
    0.43
    arie
    0.42
    POSITIVE LOGITS
     râ
    0.42
     Hart
    0.41
     Cruiser
    0.41
     కొన్ని
    0.41
    良かった
    0.41
    кова
    0.40
     ఎదు
    0.40
     Cheek
    0.39
     jScrollPane
    0.39
    煎
    0.39
    Activations Density 0.001%

    No Known Activations