© 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. 174969
    Prev
    Next
    INDEX
    Explanations

    places, objects, or actions

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

    names of leaders and greetings

    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
    做一个
    0.52
    {};
    0.51
    很多人
    0.50
    基金产品
    0.48
    ytic
    0.47
    សិក
    0.47
    首先
    0.47
    少量
    0.46
    ?");
    0.45
    نون
    0.44
    POSITIVE LOGITS
     marav
    0.48
     cavern
    0.48
     hoti
    0.46
     predefined
    0.45
     Bs
    0.44
     Maud
    0.43
     BREAK
    0.43
     poma
    0.43
     caravan
    0.42
     alab
    0.42
    Activations Density 0.001%

    No Known Activations