© 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. 163036
    Prev
    Next
    INDEX
    Explanations

    company, society, list, eg

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

    section at the end

    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
    IGHT
    0.48
    _
    0.47
    רו
    0.46
    ATE
    0.44
    imm
    0.44
    <0xF3>
    0.43
    RO
    0.43
    AV
    0.43
    GO
    0.43
    transition
    0.43
    POSITIVE LOGITS
     পরেও
    0.52
     নিয়েও
    0.50
     również
    0.49
     পরও
    0.47
    عنی
    0.45
     Đình
    0.45
     সত্ত্বেও
    0.44
     কখনই
    0.44
     Favourite
    0.43
    ኝነት
    0.42
    Activations Density 0.001%

    No Known Activations