© 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. 201084
    Prev
    Next
    INDEX
    Explanations

    security purposes

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

    Cost, Security, description

    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
     kutoka
    0.49
    एनएल
    0.48
     Gradually
    0.46
    <unused2005>
    0.45
    <unused2200>
    0.45
     بشكل
    0.44
     навчання
    0.44
     Intens
    0.43
     Geç
    0.43
     aumentando
    0.43
    POSITIVE LOGITS
     theory
    0.40
    记忆
    0.39
    czą
    0.39
     reass
    0.38
    Agent
    0.38
     থাকিলে
    0.38
    inating
    0.37
     cached
    0.37
     찾
    0.37
    AGENT
    0.37
    Activations Density 0.000%

    No Known Activations