© 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. 48863
    Prev
    Next
    INDEX
    Explanations

    older furnishings

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

    contrast and critique

    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
    ปี
    0.50
    覬
    0.47
     अंतरराष्ट्रीय
    0.46
    icur
    0.46
    સ્ટ
    0.45
    वर्ष
    0.45
     йил
    0.45
     정치
    0.44
     मुश्किल
    0.44
    詡
    0.44
    POSITIVE LOGITS
     étamines
    0.46
    чные
    0.44
     diminuer
    0.44
     responsables
    0.43
     Perfecto
    0.42
    блема
    0.42
    ebd
    0.41
     جائیں
    0.41
    FFA
    0.40
     sécr
    0.39
    Activations Density 0.000%

    No Known Activations