© 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. 188129
    Prev
    Next
    INDEX
    Explanations

    unnatural reviews

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

    negative sentiment and age

    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
    continues
    0.45
    Imm
    0.43
    Supporting
    0.40
    ACKNOWLEDGMENTS
    0.40
    <start_of_image>
    0.39
    ícios
    0.39
     homeostasis
    0.39
    INION
    0.39
     иннова
    0.38
    Innovative
    0.38
    POSITIVE LOGITS
     gece
    0.55
     madrugada
    0.49
    持ち
    0.48
     joueur
    0.47
     אחד
    0.47
     lui
    0.47
    ထား
    0.47
    밤
    0.47
     saja
    0.46
     kiedy
    0.46
    Activations Density 0.002%

    No Known Activations