© 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. 143928
    Prev
    Next
    INDEX
    Explanations

    remind, feeling, should, basis

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

    action followed by consequence

    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
    ক
    0.46
     cadast
    0.45
    の新
    0.44
    新
    0.44
    是一
    0.43
    णाल
    0.43
     devoted
    0.42
    ッ
    0.42
    チック
    0.41
    拆
    0.40
    POSITIVE LOGITS
    ;
    0.46
    ចិត្ត
    0.46
     Ethics
    0.45
     tensorflow
    0.45
     etsy
    0.44
     Protector
    0.43
     ][
    0.42
    ការពារ
    0.42
     Heidi
    0.42
    脷
    0.42
    Activations Density 0.001%

    No Known Activations