© 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. 218865
    Prev
    Next
    INDEX
    Explanations

    new covenant

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

    solid red

    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
     बेहत
    0.57
    <unused34>
    0.55
    кмекер
    0.54
    údio
    0.51
     கிரக
    0.51
    တည်
    0.50
     சே
    0.50
     obligatorio
    0.50
     ಅಂಶ
    0.49
     அனைவருக்கும்
    0.49
    POSITIVE LOGITS
    POC
    0.44
    ANN
    0.42
    ₤
    0.42
     I
    0.42
    www
    0.42
    Edward
    0.41
    AMP
    0.41
     =>
    0.41
    า
    0.41
    Nigeria
    0.40
    Activations Density 0.001%

    No Known Activations