© 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-65K
    7. 52219
    Prev
    Next
    INDEX
    Explanations

    vehicles and activities

    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_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
    ணற
    0.37
     করিয়াছে
    0.36
    ῳ
    0.36
    लेक्ट
    0.35
    ेटिव
    0.35
    bitwise
    0.35
    him
    0.35
     содержа
    0.35
    ahanan
    0.35
     Kazakh
    0.35
    POSITIVE LOGITS
    ટ
    0.46
     cars
    0.44
     اصول
    0.44
     பிரிவு
    0.44
     ríg
    0.43
     RIG
    0.42
     buil
    0.42
     percorso
    0.41
     carros
    0.41
     rig
    0.41
    Activations Density 0.053%

    No Known Activations