© 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. 22893
    Prev
    Next
    INDEX
    Explanations

    specific parts of terms

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

    maintaining systems and relationships

    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
     residents
    0.46
    侩
    0.45
     residuals
    0.45
     Residents
    0.44
    联合
    0.44
    累计
    0.44
     resident
    0.43
     scriptlevel
    0.43
     निवासी
    0.43
    苌
    0.43
    POSITIVE LOGITS
    shah
    0.50
    نام
    0.49
    اخ
    0.49
    nus
    0.48
     alkoh
    0.48
     lengkap
    0.48
    analytical
    0.47
    punyai
    0.47
    sync
    0.46
     двадцать
    0.46
    Activations Density 0.000%

    No Known Activations