© 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. 65011
    Prev
    Next
    INDEX
    Explanations

    recognize this subject matter

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

    Happy demeanor

    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
     الأبيض
    0.40
     Oxy
    0.39
    켤
    0.39
    ஸ்
    0.39
     Kerja
    0.37
     jugo
    0.37
     engan
    0.36
    萱
    0.36
    त्ता
    0.36
    nome
    0.36
    POSITIVE LOGITS
    বাংলাদেশে
    0.42
     elizabeth
    0.42
    Sydney
    0.42
    JAMES
    0.42
    琭
    0.42
    Machine
    0.41
     रुग्ण
    0.41
    ज्ञानिक
    0.39
    Aircraft
    0.39
     robert
    0.39
    Activations Density 0.001%

    No Known Activations