© 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. 27344
    Prev
    Next
    INDEX
    Explanations

    Sales, agreement, company, information

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

    system names and descriptions

    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
     وفي
    0.48
     powied
    0.47
    aloo
    0.46
    وفي
    0.45
     }];
    0.45
    currentThread
    0.45
    Cin
    0.44
    PositionY
    0.42
    ندية
    0.42
    Provider
    0.42
    POSITIVE LOGITS
     Ortega
    0.53
    警
    0.52
     Mosul
    0.51
     outweigh
    0.50
     Outback
    0.50
     GOOD
    0.49
     Woodward
    0.48
     अलर्ट
    0.48
    %"
    0.47
     Chevrolet
    0.47
    Activations Density 0.000%

    No Known Activations