© 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. 239991
    Prev
    Next
    INDEX
    Explanations

    always happy to assist

    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
     relinquished
    0.48
    ક
    0.48
     خلاف
    0.47
     durg
    0.47
     ligands
    0.46
     جانب
    0.46
     рубе
    0.44
     தெய்வ
    0.42
     Grundlage
    0.42
     університету
    0.42
    POSITIVE LOGITS
    ]
    0.64
    >,
    0.55
    repr
    0.54
     >
    0.54
     $
    0.53
    ib
    0.53
     tr
    0.52
     puse
    0.52
    ื
    0.52
    в
    0.51
    Activations Density 0.000%

    No Known Activations