© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9956
    Prev
    Next
    INDEX
    Explanations

    operations and tuning

    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
     شادی
    0.37
     पहचान
    0.33
     архівної
    0.33
     powodu
    0.32
    squa
    0.32
     déclare
    0.32
    чної
    0.32
    <unused45>
    0.32
    끽
    0.32
    اگ
    0.31
    POSITIVE LOGITS
     them
    0.75
     the
    0.66
     your
    0.59
    them
    0.52
     उन्हें
    0.49
     it
    0.48
     our
    0.47
     into
    0.47
     THEM
    0.46
     with
    0.46
    Activations Density 0.169%

    No Known Activations