© 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. 102430
    Prev
    Next
    INDEX
    Explanations

    diagram followed by explanation

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

    description, code, chopped

    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
     élect
    0.49
    ্যাড
    0.46
     플랫폼
    0.45
    
    0.45
     클
    0.45
     тыся
    0.44
     fabricant
    0.44
     innovators
    0.44
     mücade
    0.44
    平台
    0.43
    POSITIVE LOGITS
     思う
    0.47
    ija
    0.47
    et
    0.46
    ”
    0.46
     ইংরাজ
    0.46
     tadi
    0.45
     gemüt
    0.45
    lease
    0.45
    ini
    0.44
    咋
    0.44
    Activations Density 0.001%

    No Known Activations