© 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. 43774
    Prev
    Next
    INDEX
    Explanations

    multilingual words

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

    list items after directives

    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
     the
    0.31
     it
    0.29
    ,
    0.29
    …
    0.28
     “
    0.28
    ate
    0.26
    ha
    0.25
    hi
    0.25
    n
    0.25
    d
    0.25
    POSITIVE LOGITS
     wobei
    0.35
     ovales
    0.31
     ferrugineux
    0.31
     ausgeführt
    0.31
     eller
    0.31
     എന്നീ
    0.30
     এছাড়াও
    0.30
     utilisent
    0.30
     ซึ่ง
    0.29
     maintenir
    0.29
    Activations Density 0.314%

    No Known Activations