© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9150
    Prev
    Next
    INDEX
    Explanations

    names of places and camera brands

    np_acts-logits-general · gemini-2.5-flash-lite

    Indian states and car brands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slovakia
    0.46
    ombang
    0.44
    。。。。
    0.43
    塹
    0.42
     Slovak
    0.42
     Youngstown
    0.41
     dn
    0.39
     sloppy
    0.39
    滦
    0.38
    ropolis
    0.38
    POSITIVE LOGITS
     Dorset
    0.97
     Bournemouth
    0.84
     कटोच
    0.73
     Subaru
    0.68
     Christchurch
    0.64
     हिमाचल
    0.63
     कर्नाटक
    0.62
     Wessex
    0.58
     धर्मशाला
    0.57
     Hampshire
    0.57
    Activations Density 0.259%

    No Known Activations