© 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. 36643
    Prev
    Next
    INDEX
    Explanations

    Precautions, numbers, currency, specific items

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

    code or technical terms

    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
    ↵
    0.38
     Envi
    0.36
     Capt
    0.35
     ή
    0.35
    ée
    0.34
     Inc
    0.34
     hvert
    0.34
    ή
    0.34
     Quantum
    0.34
     rue
    0.34
    POSITIVE LOGITS
     TNumber
    0.40
    $\--
    0.38
     तळ
    0.36
     তৃতীয়
    0.36
    ESTER
    0.35
    FindAction
    0.35
    Nickel
    0.35
    Floor
    0.35
    एशन
    0.35
     반지
    0.34
    Activations Density 0.010%

    No Known Activations