© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9465
    Prev
    Next
    INDEX
    Explanations

    she or her

    np_acts-logits-general · gemini-2.5-flash-lite

    she after punctuation or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite

    female pronouns

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esso
    1.07
     dets
    0.90
    ньому
    0.84
     அவனை
    0.79
     അദ്ദേഹം
    0.75
     അദ്ദേഹ
    0.74
     करतो
    0.66
     îl
    0.62
     dessen
    0.61
     অভিনে
    0.59
    POSITIVE LOGITS
    她的
    3.98
     그녀
    3.69
    她在
    3.63
     her
    3.53
    彼女
    3.48
    她
    3.42
     её
    3.33
     ее
    3.31
     її
    3.25
     ఆమె
    3.22
    Activations Density 1.747%

    No Known Activations