© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22292
    Prev
    Next
    INDEX
    Explanations

    il sequences followed by names or words

    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
     wizard
    0.43
    ynchron
    0.39
     NIE
    0.39
    zą
    0.39
     NgModule
    0.38
     OWL
    0.38
     rallying
    0.37
    ᓛ
    0.37
     apple
    0.37
     magnum
    0.37
    POSITIVE LOGITS
    billy
    0.52
    Hil
    0.43
    젼
    0.41
    Tilt
    0.41
    قر
    0.40
    ilit
    0.40
    قب
    0.40
    HIV
    0.39
    potent
    0.38
     Billie
    0.38
    Activations Density 0.041%

    No Known Activations