© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6388
    Prev
    Next
    INDEX
    Explanations

    Plugin creation code documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
    кте
    0.57
    }}}}
    0.57
    ப்பிட
    0.55
    lytres
    0.55
     দৃষ্টান্ত
    0.54
    ophores
    0.53
    asson
    0.52
     }^{[
    0.52
     تحديد
    0.52
    সিড
    0.52
    POSITIVE LOGITS
     पुजारी
    0.63
    掬
    0.55
     perjury
    0.54
    wein
    0.52
    経営
    0.52
    郡
    0.51
     department
    0.50
    豐
    0.50
     ऑडिट
    0.50
    サプライ
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.