© 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. 31-GEMMASCOPE-2-RES-262K
    7. 179422
    Prev
    Next
    INDEX
    Explanations

    soul mate

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

    Regarding employee or fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ن
    0.53
     they
    0.50
    ं
    0.49
    yya
    0.49
     Thorpe
    0.48
     Intern
    0.48
     ataxia
    0.47
    IA
    0.47
    т
    0.47
    то
    0.46
    POSITIVE LOGITS
     والص
    0.51
     அறிவியல்
    0.51
     სპეცი
    0.49
     μια
    0.47
    archiw
    0.47
    ünstler
    0.46
    வியல்
    0.45
     രംഗ
    0.45
    getBlue
    0.45
    ähl
    0.45
    Activations Density 0.000%

    No Known Activations