© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213716
    Prev
    Next
    INDEX
    Explanations

    old man Tiber

    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
     "
    0.47
     intellectual
    0.47
     Intellectual
    0.45
     arbit
    0.43
    arithmic
    0.41
     cosmic
    0.41
    kovskij
    0.41
     empirical
    0.40
    解析
    0.40
     torrent
    0.40
    POSITIVE LOGITS
     Kiara
    0.49
     jefe
    0.47
    꿍
    0.47
     देशभर
    0.47
     پیشہ
    0.46
    俺
    0.46
     moradores
    0.46
     davvero
    0.45
     taco
    0.45
    úrate
    0.45
    Activations Density 0.010%

    No Known Activations