© 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-16K
    7. 9150
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_40_width_16k_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
     gig
    0.43
     NSR
    0.42
     guild
    0.41
    ropolis
    0.41
     Slovak
    0.41
     families
    0.40
     सरा
    0.40
    塹
    0.40
     mine
    0.39
    umina
    0.39
    POSITIVE LOGITS
     Subaru
    0.76
     Dorset
    0.68
     Christchurch
    0.62
     कटोच
    0.62
     Bournemouth
    0.55
     हिमाचल
    0.53
    邛
    0.50
     कर्नाटक
    0.50
     Himachal
    0.47
    郫
    0.47
    Activations Density 0.090%

    No Known Activations