© 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. 77828
    Prev
    Next
    INDEX
    Explanations

    accountability and accuracy

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

    principles and target concepts

    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
    댐
    0.48
     terminated
    0.46
     중간
    0.45
     GST
    0.45
     aborted
    0.44
    ged
    0.44
     blown
    0.43
     ď
    0.43
     freed
    0.43
     purporting
    0.43
    POSITIVE LOGITS
    नेता
    0.46
     चिकित्स
    0.43
    Interestingly
    0.43
     Painters
    0.43
     невро
    0.43
     আত্ম
    0.43
    ]_
    0.43
    Patients
    0.43
    Painter
    0.42
    icklabels
    0.42
    Activations Density 0.002%

    No Known Activations