© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48432
    Prev
    Next
    INDEX
    Explanations

    Zoho, Zoë, zoophilia

    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_40_width_65k_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
     consuming
    0.42
     டி
    0.38
    泽
    0.38
     Stoner
    0.37
     übers
    0.36
     Relaxation
    0.36
     জা
    0.36
    ကိုယ်
    0.35
     Пер
    0.35
    ulers
    0.35
    POSITIVE LOGITS
     zo
    0.41
     yellows
    0.40
    Zo
    0.39
     зо
    0.38
     黄
    0.36
    зо
    0.36
    ದ್ಯ
    0.36
    Otherwise
    0.36
     wiecz
    0.35
     senc
    0.35
    Activations Density 0.011%

    No Known Activations