© 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. 500
    Prev
    Next
    INDEX
    Explanations

    method calls or property access

    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
     tumeur
    0.52
     tumeurs
    0.52
    醣
    0.51
     Textured
    0.50
     അന്നനാള
    0.49
    醀
    0.49
    textured
    0.49
    蒴
    0.48
    郸
    0.48
    扦
    0.47
    POSITIVE LOGITS
    state
    0.55
     state
    0.52
    name
    0.52
     p
    0.48
     n
    0.48
     va
    0.48
     at
    0.48
    _
    0.48
    n
    0.47
     c
    0.47
    Activations Density 0.062%

    No Known Activations