© 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. 3572
    Prev
    Next
    INDEX
    Explanations

    deliberately shrouded

    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
    ktional
    0.77
     മാത്രമല്ല
    0.66
    ার্
    0.65
    镊
    0.64
    acart
    0.64
    jiv
    0.63
     cheat
    0.63
    OnUiThread
    0.63
     relive
    0.62
    🎧
    0.61
    POSITIVE LOGITS
     unknown
    4.73
     Unknown
    4.25
    Unknown
    4.21
    unknown
    4.11
     unknowns
    3.97
     uncertain
    3.78
     unclear
    3.70
     неизвест
    3.66
     undetermined
    3.62
     unidentified
    3.57
    Activations Density 1.255%

    No Known Activations