© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 27244
    Prev
    Next
    INDEX
    Explanations

    not intended or resumed

    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_31_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
    ад
    0.53
    rzed
    0.49
    䉍
    0.49
     فِي
    0.49
    as
    0.46
    КУ
    0.45
    each
    0.45
    zt
    0.45
    legisl
    0.44
    我們
    0.44
    POSITIVE LOGITS
     Isot
    0.47
    ئین
    0.44
     Massage
    0.40
    醤
    0.40
     Jet
    0.39
     Racial
    0.39
     没有
    0.39
    专属
    0.38
     cotton
    0.38
     spaceship
    0.38
    Activations Density 0.001%

    No Known Activations