© 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-16K
    7. 12725
    Prev
    Next
    INDEX
    Explanations

    free or fee

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

    authentication or connectivity phrases

    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_16k_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
     কাছ
    0.48
     environs
    0.46
     erlä
    0.46
     THAT
    0.44
     Ole
    0.44
     I
    0.43
     Marin
    0.43
     Presses
    0.43
     முயற்சி
    0.43
     Ames
    0.43
    POSITIVE LOGITS
    ਗੇ
    0.57
    chocolate
    0.50
    ia
    0.50
    tcpHeader
    0.48
    audioType
    0.47
    મિત
    0.47
    getNumber
    0.46
    の高
    0.46
    뜻
    0.46
    یک
    0.46
    Activations Density 0.000%

    No Known Activations