© 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. 143992
    Prev
    Next
    INDEX
    Explanations

    referred

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

    limitation of models

    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
    ^{\
    0.50
     革
    0.50
    aronne
    0.48
    ixon
    0.47
    Foldout
    0.47
    ご注文
    0.47
    udp
    0.46
    itm
    0.46
     автомобиль
    0.45
     formant
    0.45
    POSITIVE LOGITS
    м
    0.62
    ம்
    0.50
    م
    0.49
     Referred
    0.45
    ும்
    0.44
    ්‍ර
    0.44
    ங்கும்
    0.44
     referred
    0.44
    ड़िया
    0.43
    )\}
    0.42
    Activations Density 0.000%

    No Known Activations