© 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. 134347
    Prev
    Next
    INDEX
    Explanations

    looking for

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

    because of assumptions

    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
     উদ্বিগ্ন
    0.52
    ետ
    0.45
     பூஜ
    0.44
    䳕
    0.44
    оні
    0.41
    㑓
    0.41
    وكان
    0.40
    剻
    0.40
    拿起
    0.40
    㷌
    0.39
    POSITIVE LOGITS
    r
    0.55
    strstr
    0.46
     a
    0.46
    type
    0.46
    yn
    0.46
    depart
    0.46
     type
    0.45
     células
    0.45
    ville
    0.45
    lymph
    0.44
    Activations Density 0.001%

    No Known Activations