© 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. 193585
    Prev
    Next
    INDEX
    Explanations

    Ruth and associated names

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

    Ruth or Eve names

    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
    ী
    0.71
    ት
    0.57
     שלך
    0.55
    ை
    0.54
     estánd
    0.52
     chuyện
    0.52
     करणारे
    0.52
    ция
    0.51
     그녀
    0.50
    䢎
    0.50
    POSITIVE LOGITS
    ف
    0.65
    EN
    0.61
    EF
    0.60
    EK
    0.60
    O
    0.57
    EP
    0.57
    OB
    0.56
    OU
    0.56
    EV
    0.55
    OT
    0.54
    Activations Density 0.001%

    No Known Activations