© 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. 145809
    Prev
    Next
    INDEX
    Explanations

    representative sample, payment, define

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

    second place

    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
     Texts
    0.51
     Receipts
    0.50
    Essentials
    0.50
    0.50
    ↵
    0.49
    Copy
    0.48
     Invisible
    0.48
     Truth
    0.48
    Pit
    0.48
     ഒരിക്ക
    0.47
    POSITIVE LOGITS
     hicimos
    0.54
     habíamos
    0.49
     habían
    0.48
    <unused2222>
    0.48
     punctatis
    0.47
    aliśmy
    0.46
     unanim
    0.44
     unanimously
    0.44
     ponctué
    0.44
     glorious
    0.44
    Activations Density 0.001%

    No Known Activations