© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245059
    Prev
    Next
    INDEX
    Explanations

    Enza helped make

    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
    protective
    0.50
     tumultuous
    0.46
    ාර
    0.45
    ʿ
    0.44
     chromosomal
    0.44
     five
    0.43
    5
    0.43
     freezing
    0.42
    зим
    0.42
     controllable
    0.42
    POSITIVE LOGITS
     ця
    0.53
    堞
    0.52
     وە
    0.51
    CheckBox
    0.50
    办法
    0.49
    鳅
    0.48
    Denominator
    0.48
    单击
    0.48
    ChatItem
    0.48
    Samples
    0.47
    Activations Density 0.000%

    No Known Activations