© 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-16K
    7. 11735
    Prev
    Next
    INDEX
    Explanations

    as you can see

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

    as you can see

    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_16k_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
    bandage
    0.46
    spine
    0.45
    spinal
    0.42
    сли
    0.41
     चलने
    0.40
    برد
    0.40
    ماع
    0.40
    }$$
    0.39
    amounts
    0.39
    (
    0.39
    POSITIVE LOGITS
    गुना
    0.43
     PAY
    0.42
     payee
    0.42
     लगती
    0.41
     স্টক
    0.39
     Horne
    0.39
    мпа
    0.39
     Raya
    0.39
     riječi
    0.38
     phạm
    0.38
    Activations Density 0.002%

    No Known Activations