© 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. 31-GEMMASCOPE-2-RES-262K
    7. 126872
    Prev
    Next
    INDEX
    Explanations

    edited compilation of existing

    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
    agamanam
    0.44
    \<
    0.44
    ⒎
    0.43
    bcrypt
    0.42
     ошибки
    0.42
    errors
    0.42
    yelination
    0.42
     devra
    0.42
     같습니다
    0.41
    𝚢
    0.41
    POSITIVE LOGITS
     system
    0.46
     celebrity
    0.46
     information
    0.45
     welcomed
    0.43
     network
    0.42
     markt
    0.42
     informazioni
    0.41
     market
    0.41
    cio
    0.41
    Infos
    0.41
    Activations Density 0.001%

    No Known Activations