© 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. 211377
    Prev
    Next
    INDEX
    Explanations

    Guaranty broker cohorts bait Obama maximum

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

    Google Ads

    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
     sạch
    0.45
    ťou
    0.45
     maquillaje
    0.45
    し
    0.44
    損
    0.44
    ាញ
    0.43
     gummy
    0.42
     harshly
    0.41
     empirically
    0.41
     ginger
    0.40
    POSITIVE LOGITS
     waardoor
    0.46
     въз
    0.45
    IK
    0.43
     वाप
    0.41
    adisu
    0.41
    IVACON
    0.41
    }$;
    0.40
     trasfer
    0.40
     બાદ
    0.38
     մե
    0.38
    Activations Density 0.000%

    No Known Activations