© 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. 223048
    Prev
    Next
    INDEX
    Explanations

    issues and advice

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

    information and context

    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
    ING
    0.54
    扎
    0.46
    束
    0.45
    紮
    0.41
    ทย์
    0.39
    캡
    0.39
    萩
    0.39
    Activation
    0.38
    Injection
    0.38
    }=$
    0.37
    POSITIVE LOGITS
    یم
    0.48
     pretende
    0.47
     //}
    0.47
     reaff
    0.46
     quelconque
    0.45
    میل
    0.44
     concedes
    0.44
     wypeł
    0.44
     restantes
    0.44
     gehö
    0.43
    Activations Density 0.000%

    No Known Activations