© 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. 201038
    Prev
    Next
    INDEX
    Explanations

    assessing plausibility

    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
     amplify
    0.46
     मासिक
    0.43
     நன்ற
    0.43
    र्वे
    0.42
     Пан
    0.42
     développ
    0.41
    พัน
    0.41
    战
    0.41
    वेयर
    0.41
     rehabilitate
    0.41
    POSITIVE LOGITS
     luggage
    0.50
     hindi
    0.44
    లూ
    0.43
    adamia
    0.43
    '
    0.43
    Hindi
    0.42
     қара
    0.41
     berada
    0.41
    csak
    0.40
     robbery
    0.40
    Activations Density 0.001%

    No Known Activations