© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19808
    Prev
    Next
    INDEX
    Explanations

    comes to mind

    np_acts-logits-general · gemini-2.5-flash-lite

    all users, safety, reset account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0xA8>
    0.54
    ཾ
    0.48
    ib
    0.47
     causar
    0.46
     confirmé
    0.45
     divulg
    0.44
     Evangel
    0.44
    etermined
    0.43
    becomes
    0.43
     favorita
    0.43
    POSITIVE LOGITS
    检索
    0.51
    软件
    0.49
    东西
    0.47
     pripad
    0.46
    网站
    0.46
    更改
    0.45
    遌
    0.45
    ర్జ
    0.44
     Sails
    0.44
    蠡
    0.44
    Activations Density 0.000%

    No Known Activations