© 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-262K
    7. 221486
    Prev
    Next
    INDEX
    Explanations

    old and young, father, friend, man, aging

    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_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
     ライト
    0.46
    ライト
    0.42
    阠
    0.41
     പൊലീസ്
    0.40
     Sank
    0.39
     вики
    0.39
    lccc
    0.39
    ᖇ
    0.39
    numpy
    0.38
    VISIBLE
    0.38
    POSITIVE LOGITS
    יא
    0.42
    撾
    0.37
    ased
    0.37
     pares
    0.37
    wa
    0.35
    irmat
    0.35
     demanding
    0.35
    ogan
    0.35
     hotly
    0.35
    oyer
    0.34
    Activations Density 0.001%

    No Known Activations