© 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-65K
    7. 28300
    Prev
    Next
    INDEX
    Explanations

    highlight key aspects

    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_65k_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
    л
    0.74
    ล
    0.74
     as
    0.63
    ल
    0.59
    ov
    0.58
     upregulation
    0.56
    b
    0.55
     addiction
    0.54
     that
    0.53
     Democratic
    0.52
    POSITIVE LOGITS
    માં
    0.82
    மாக
    0.80
    突出
    0.77
     highlight
    0.75
    。
    0.74
     emphasised
    0.72
    وين
    0.70
    強調
    0.69
    ারি
    0.68
    强调
    0.68
    Activations Density 0.061%

    No Known Activations