© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5341
    Prev
    Next
    INDEX
    Explanations

    initial cash outlay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     rivets
    1.20
    pport
    1.02
     உலகின்
    0.99
     squats
    0.98
    谣
    0.97
    ਸੀ
    0.97
    পৃথিব
    0.96
     rebels
    0.96
    arriv
    0.95
    سي
    0.94
    POSITIVE LOGITS
    в
    1.20
     searchTerm
    1.12
    urved
    1.11
     ache
    1.04
     printr
    1.02
     (|
    1.00
     conjugate
    0.99
     mencionado
    0.98
     refrain
    0.96
    கு
    0.95
    Activations Density 0.000%

    No Known Activations