© 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-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 10929
    Prev
    Next
    INDEX
    Explanations

    reading file lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
        
    0.35
    0.35
    ↵
    0.34
    0.33
            
    0.30
    ?>
    0.30
                
    0.29
     /*
    0.29
     //
    0.28
     afferma
    0.28
    POSITIVE LOGITS
    सर्गिक
    0.34
    ísk
    0.33
    ewer
    0.32
     له‌
    0.32
    तेक
    0.32
     व्हाउचर
    0.32
     केवळ
    0.32
    opolymers
    0.32
    cluding
    0.31
    iphatic
    0.31
    Activations Density 0.011%

    No Known Activations