© 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. 21195
    Prev
    Next
    INDEX
    Explanations

    versioned software and financial rounds

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

    Fibonacci retracements, tiered approach

    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
     vì
    0.41
     किंवा
    0.40
    兰
    0.38
     Mitochond
    0.38
    azepam
    0.37
    蘭
    0.37
    銀行
    0.36
     मिन
    0.36
     anderes
    0.36
     Electrons
    0.36
    POSITIVE LOGITS
    
    0.42
     eventful
    0.41
     tailored
    0.40
     pivotal
    0.40
     glimpses
    0.40
     את
    0.40
     redefine
    0.40
     unveiling
    0.39
     répertoire
    0.39
     prelude
    0.38
    Activations Density 0.000%

    No Known Activations