© 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. 150997
    Prev
    Next
    INDEX
    Explanations

    yield and more efficiency

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

    financial and 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
     независимо
    0.51
     деб
    0.50
     becoming
    0.49
     unsurprisingly
    0.48
     இன்றைய
    0.46
    ">→</
    0.46
    それを
    0.46
     சரியாக
    0.46
     impatient
    0.46
     vehement
    0.45
    POSITIVE LOGITS
     নিয়ে
    0.49
     radionu
    0.42
     নিয়ে
    0.42
     depre
    0.42
    胴
    0.41
    拟
    0.40
     مگر
    0.40
    仪
    0.40
     depreciation
    0.40
    分の
    0.40
    Activations Density 0.000%

    No Known Activations