© 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. 110512
    Prev
    Next
    INDEX
    Explanations

    Google searches and services

    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
    '
    0.63
    '،
    0.47
    Lecture
    0.47
     Together
    0.47
     Sind
    0.47
    This
    0.46
     zusammen
    0.46
    ‘
    0.43
    Definition
    0.43
     Dining
    0.43
    POSITIVE LOGITS
     droplets
    0.54
     lawmakers
    0.51
     midwives
    0.50
     medics
    0.49
     painkillers
    0.48
     officials
    0.46
     pillows
    0.46
     firefighters
    0.46
     wrongful
    0.46
     ഒഴിവാ
    0.46
    Activations Density 0.006%

    No Known Activations