© 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. 138719
    Prev
    Next
    INDEX
    Explanations

    kindness and in

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

    reason for varieties

    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
     K
    0.44
     Strasbourg
    0.42
     Y
    0.42
     একটী
    0.41
     CE
    0.41
     percentage
    0.41
     SSL
    0.41
     change
    0.41
    k
    0.40
     Rehman
    0.40
    POSITIVE LOGITS
    ائیگی
    0.50
    destination
    0.50
     luxuries
    0.49
     devons
    0.48
     ধরণের
    0.48
    ప్రత్యర్థి
    0.48
     النوع
    0.47
    ប្រភេទ
    0.47
     doit
    0.46
    ड्रन
    0.46
    Activations Density 0.000%

    No Known Activations