© 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. 120650
    Prev
    Next
    INDEX
    Explanations

    more approach

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

    types of approaches

    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
     मटेरियल
    0.54
    били
    0.48
     Матери
    0.47
    ಉ
    0.46
    𝟮
    0.45
    κολ
    0.43
     matériel
    0.43
     विश्वसनीय
    0.42
     zuverläss
    0.42
    Լ
    0.42
    POSITIVE LOGITS
     approach
    0.96
    approach
    0.83
     Approach
    0.82
     подход
    0.78
     подхода
    0.76
     approche
    0.71
     approaches
    0.70
     pendekatan
    0.70
     yaklaş
    0.69
    Approach
    0.69
    Activations Density 0.031%

    No Known Activations