© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11093
    Prev
    Next
    INDEX
    Explanations

    pronouns she and he

    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_9_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
    倆
    0.93
    archy
    0.91
    doesn
    0.80
    д
    0.76
    Doesn
    0.74
     চুলের
    0.73
    |=|
    0.71
    uristic
    0.70
    ão
    0.70
    俩
    0.70
    POSITIVE LOGITS
    ्स
    0.97
    ের
    0.84
     Fondation
    0.80
     toute
    0.79
     ét
    0.78
    اً
    0.78
    য়ের
    0.77
     candid
    0.76
     petits
    0.76
     critic
    0.76
    Activations Density 0.061%

    No Known Activations