© 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. 221124
    Prev
    Next
    INDEX
    Explanations

    brand, service, or function followed by related terms

    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
     que
    0.40
    』
    0.39
    зь
    0.39
     cures
    0.39
     Que
    0.38
    zka
    0.37
    ILabel
    0.37
     patiently
    0.36
     homogenized
    0.36
    Que
    0.36
    POSITIVE LOGITS
    InstrumentedTest
    0.45
     '{}
    0.45
     अन्तर
    0.41
     फीट
    0.40
     eyelid
    0.39
     nurseries
    0.39
    眼的
    0.39
     costumbre
    0.39
     कम
    0.38
     मिनट
    0.37
    Activations Density 0.000%

    No Known Activations