© 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. 4527
    Prev
    Next
    INDEX
    Explanations

    phone numbers, temperature, rows

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

    table rows or columns

    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
    روش
    0.48
     تهران
    0.48
     viciss
    0.47
    燔
    0.47
    箇
    0.47
     stwier
    0.47
     służ
    0.46
    گە
    0.45
    侔
    0.45
    Merci
    0.44
    POSITIVE LOGITS
     row
    0.46
    row
    0.45
     />
    0.43
    ;
    0.42
     else
    0.41
    ];
    0.40
     Row
    0.40
    <0x80>
    0.40
     ]
    0.40
    <0x0D>
    0.40
    Activations Density 0.002%

    No Known Activations