© 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. 150809
    Prev
    Next
    INDEX
    Explanations

    technical agreement

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

    annual monthly income

    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
    Ро
    0.55
    _
    0.50
    най
    0.48
     Donuts
    0.47
    <0xE3>
    0.45
    Mang
    0.45
     Irak
    0.45
    O
    0.45
     सड़कें
    0.44
    Мне
    0.44
    POSITIVE LOGITS
     recalculated
    0.54
     tutor
    0.54
     reallocation
    0.49
     discounting
    0.47
     ಔಷ
    0.46
     devoting
    0.46
     borrowing
    0.45
     recalcul
    0.45
     deducting
    0.45
     tuberc
    0.45
    Activations Density 0.006%

    No Known Activations