© 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. 10828
    Prev
    Next
    INDEX
    Explanations

    actions following "to" or comma

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

    make steady or stable

    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
     или
    0.44
     veya
    0.42
    或者是
    0.41
     hoặc
    0.40
    anjutnya
    0.40
     शासकीय
    0.40
    瑀
    0.40
     ή
    0.40
    多次
    0.39
    ामध्ये
    0.39
    POSITIVE LOGITS
     concurrence
    0.42
     leeway
    0.40
     botany
    0.39
     bruit
    0.37
     willful
    0.36
     jeito
    0.36
     wickedness
    0.36
     बखूबी
    0.36
    Sally
    0.36
    мпаваць
    0.36
    Activations Density 0.003%

    No Known Activations