© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 79602
    Prev
    Next
    INDEX
    Explanations

    information sources and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    भ
    0.49
     Okinawa
    0.46
     valori
    0.46
     Madagascar
    0.46
     Algarve
    0.44
     necklace
    0.44
     Burundi
    0.44
    기
    0.44
     Lato
    0.43
     Langevin
    0.43
    POSITIVE LOGITS
     செ
    0.46
    ience
    0.45
     был
    0.44
    不會
    0.44
    ância
    0.44
     скри
    0.43
    எஸ்
    0.42
    鵝
    0.42
    urang
    0.41
    న్స్‌
    0.41
    Activations Density 0.001%

    No Known Activations