© 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. 20067
    Prev
    Next
    INDEX
    Explanations

    making use of tools

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

    Cosine values and tools

    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
    ʲ
    0.39
    LOGGER
    0.38
    Mt
    0.38
    Sta
    0.38
    Public
    0.36
    November
    0.36
    Nr
    0.35
    №
    0.35
    Nation
    0.35
    ほ
    0.35
    POSITIVE LOGITS
     eingesetzt
    0.58
     megfelelő
    0.50
     utilisées
    0.50
     nécessaires
    0.48
     chadd
    0.48
     toolkit
    0.46
     Einf
    0.46
     استخدم
    0.45
     outil
    0.45
    厙
    0.44
    Activations Density 0.000%

    No Known Activations