© 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. 27945
    Prev
    Next
    INDEX
    Explanations

    mid-range phones and prices

    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
     CarPlay
    0.49
    Rigidbody
    0.47
     touchscreen
    0.45
    Apple
    0.44
     Apple
    0.44
     童
    0.42
    雄
    0.42
    苹果
    0.42
    ገልግሎ
    0.41
     mapView
    0.41
    POSITIVE LOGITS
     launched
    0.55
     lancio
    0.52
    launched
    0.51
     Philippines
    0.50
     mid
    0.47
     Indian
    0.47
     launches
    0.46
     India
    0.46
     launch
    0.46
     பட்
    0.45
    Activations Density 0.003%

    No Known Activations