© 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. 196782
    Prev
    Next
    INDEX
    Explanations

    value for your time

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

    injecting external knowledge

    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
    (
    0.50
     vino
    0.48
    ?
    0.47
    :
    0.47
     lintas
    0.47
     archivo
    0.46
    僱
    0.46
     titel
    0.46
    য়ের
    0.45
    ផ្ល
    0.45
    POSITIVE LOGITS
    става
    0.45
    腈
    0.45
    洳
    0.44
     일정
    0.43
    越高
    0.42
    हरण
    0.40
    унд
    0.40
     സൂര്യ
    0.40
    requirements
    0.40
    越
    0.40
    Activations Density 0.000%

    No Known Activations