© 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. 136211
    Prev
    Next
    INDEX
    Explanations

    internet pages

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

    varying/adapting/can be

    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
     أو
    0.53
    +,
    0.48
    +',
    0.47
    ®,
    0.46
     或者
    0.46
    “,
    0.46
    ي
    0.46
    °,
    0.45
    ²,
    0.45
    +",
    0.45
    POSITIVE LOGITS
     বিস্মিত
    0.47
    อยู่ใน
    0.46
     সংবাদ
    0.45
    রাতে
    0.45
    禟
    0.45
    烪
    0.45
     उत्सव
    0.44
    迎
    0.44
    ต่อไป
    0.42
    บล
    0.42
    Activations Density 0.001%

    No Known Activations