© 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. 203166
    Prev
    Next
    INDEX
    Explanations

    Halloween party, canceled before

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

    quantitative information

    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
     Hamiltonian
    0.51
     T
    0.50
     TE
    0.50
     j
    0.48
     også
    0.47
     t
    0.46
     van
    0.46
     detto
    0.46
     ook
    0.46
     Y
    0.46
    POSITIVE LOGITS
    鲮
    0.51
    quantidade
    0.48
    efficacité
    0.47
    améliorer
    0.47
    Extraction
    0.46
    onać
    0.46
    ຂໍ້ມ
    0.46
     unusable
    0.46
    evaluated
    0.46
    amélioration
    0.45
    Activations Density 0.001%

    No Known Activations