© 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. 40-GEMMASCOPE-2-RES-262K
    7. 35816
    Prev
    Next
    INDEX
    Explanations

    reporting actions and events

    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_40_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
     Mr
    0.44
     trembling
    0.43
     Mrs
    0.42
     Patrim
    0.40
    當時
    0.39
     তোলেন
    0.39
    જબ
    0.39
    茛
    0.39
    Mrs
    0.38
    ദ്യം
    0.38
    POSITIVE LOGITS
     arrived
    0.68
     returned
    0.62
     llegó
    0.61
    回来了
    0.60
     pasó
    0.59
     went
    0.58
     underwent
    0.57
     flew
    0.55
     chegou
    0.55
     llegaron
    0.54
    Activations Density 0.000%

    No Known Activations