© 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. 88909
    Prev
    Next
    INDEX
    Explanations

    legal advice and photography advice

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

    business and finance terms

    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
     boxe
    0.50
    Hx
    0.47
    cede
    0.45
    LoginPage
    0.42
    ckte
    0.42
     jeep
    0.41
    𝐬
    0.41
     cages
    0.40
     commen
    0.40
    ዳል
    0.40
    POSITIVE LOGITS
    你
    0.53
    把
    0.50
    тами
    0.48
     把
    0.47
     страны
    0.47
     Kamu
    0.47
     好
    0.46
     감
    0.45
     transcoding
    0.45
     சின்ன
    0.45
    Activations Density 0.003%

    No Known Activations