© 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-16K
    7. 9130
    Prev
    Next
    INDEX
    Explanations

    old man, old school

    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_16k_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
     enumerate
    0.43
     lifespan
    0.43
    acken
    0.40
    だった
    0.38
     posticis
    0.38
     पछ
    0.37
     length
    0.37
    澳
    0.37
    افظ
    0.37
     leicht
    0.36
    POSITIVE LOGITS
     fashioned
    0.97
    fashioned
    0.95
     old
    0.89
     Old
    0.83
     OLD
    0.82
    Old
    0.77
     adage
    0.76
    旧
    0.75
    old
    0.75
     viejo
    0.73
    Activations Density 0.062%

    No Known Activations