© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47455
    Prev
    Next
    INDEX
    Explanations

    girlfriend or partner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    t
    0.53
    es
    0.49
    is
    0.49
    ing
    0.47
    z
    0.47
     ಯು
    0.47
    s
    0.47
    tahun
    0.46
    table
    0.44
    n
    0.44
    POSITIVE LOGITS
     иногда
    0.47
     entrop
    0.46
    AuthProvider
    0.46
    驷
    0.44
    цей
    0.44
    蜞
    0.44
     bent
    0.43
     cathodes
    0.43
     attrakt
    0.43
     saddles
    0.42
    Activations Density 0.002%

    No Known Activations