© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106207
    Prev
    Next
    INDEX
    Explanations

    promiscuous mode, sexual, teleology, association

    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_16_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
    <0x0D>
    0.73
    h
    0.60
     by
    0.56
    '
    0.54
     compositor
    0.54
    া
    0.54
    a
    0.53
     director
    0.51
     to
    0.49
     year
    0.49
    POSITIVE LOGITS
     operativos
    0.62
    鱔
    0.56
     benefícios
    0.55
    ೇವ
    0.55
     preferências
    0.55
    <unused1865>
    0.54
    ಟ್ರ
    0.54
    oxygen
    0.52
     όταν
    0.51
     ಲಾ
    0.51
    Activations Density 0.000%

    No Known Activations