© 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. 31-GEMMASCOPE-2-RES-262K
    7. 11327
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols

    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
    噔
    0.45
     pcMove
    0.45
    ЗИ
    0.44
     রেজিম
    0.44
    Ң
    0.44
    痞
    0.43
    嬷
    0.43
    ቶችን
    0.42
    ПК
    0.42
     सीखते
    0.42
    POSITIVE LOGITS
    \
    0.58
    _
    0.55
     meie
    0.47
     società
    0.44
    ên
    0.43
    uan
    0.43
    )
    0.43
    ir
    0.42
    êu
    0.42
    )，
    0.42
    Activations Density 0.002%

    No Known Activations