© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43873
    Prev
    Next
    INDEX
    Explanations

    words of high praise

    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
    뗄
    0.55
     खास
    0.52
    т
    0.52
    ногда
    0.49
    д
    0.48
     on
    0.47
     દરેક
    0.47
     ऑन
    0.47
     каждый
    0.46
    𝓈
    0.46
    POSITIVE LOGITS
     magnific
    0.72
     splendid
    0.69
     magnificent
    0.66
     marvell
    0.60
     marvellous
    0.57
     magní
    0.57
     brilliant
    0.56
     excellent
    0.54
     excellence
    0.54
     wonderfully
    0.53
    Activations Density 0.025%

    No Known Activations