© 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. 61109
    Prev
    Next
    INDEX
    Explanations

    collocations

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

    smtp server

    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
     I
    0.54
     provisional
    0.53
     pleasures
    0.53
     depressed
    0.52
     taut
    0.52
     suspense
    0.51
     sagging
    0.51
     pinched
    0.51
     mentally
    0.50
     just
    0.50
    POSITIVE LOGITS
    ধ
    0.55
    例如
    0.54
    टाइ
    0.53
    ľov
    0.52
    트
    0.50
    וו
    0.50
    드시
    0.50
    또한
    0.50
    위
    0.49
     قال
    0.49
    Activations Density 0.000%

    No Known Activations