© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3055
    Prev
    Next
    INDEX
    Explanations

    platforms and intermediaries

    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_29_width_65k_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
     sabiduría
    0.94
     superstition
    0.86
     outbursts
    0.84
     เขียน
    0.82
     والله
    0.81
     superstitious
    0.80
    '`--'`--
    0.79
    を示
    0.79
     degeneration
    0.79
     joyous
    0.79
    POSITIVE LOGITS
     outsourced
    1.46
     outsource
    1.45
     outsourcing
    1.40
     platforms
    1.40
     intermedi
    1.39
     facilitating
    1.38
     partnering
    1.37
     middlemen
    1.31
     platform
    1.29
     brokerage
    1.28
    Activations Density 1.158%

    No Known Activations