© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55286
    Prev
    Next
    INDEX
    Explanations

    used mattress

    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
    ल्पनिक
    0.50
    اداسی
    0.50
    "*
    0.48
     listop
    0.47
    杼
    0.47
    "。
    0.46
    EMENTS
    0.46
     समर्पित
    0.46
    जारत
    0.46
     Lanzarote
    0.45
    POSITIVE LOGITS
     and
    0.48
    ,
    0.46
    and
    0.46
     और
    0.44
     và
    0.43
     এবং
    0.42
     и
    0.41
     και
    0.40
     dhe
    0.39
    ’
    0.39
    Activations Density 0.008%

    No Known Activations