© 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. 202575
    Prev
    Next
    INDEX
    Explanations

    busy pushing

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

    social media interactions and reactions

    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
    ın
    0.50
    में
    0.47
    나
    0.46
    స్త
    0.45
     क्षार
    0.45
     ప్రయత్
    0.44
    یک
    0.43
     podia
    0.43
    
    0.43
    amides
    0.43
    POSITIVE LOGITS
     Father
    0.53
     sujet
    0.47
     Cabernet
    0.47
     Cayenne
    0.46
     Godfather
    0.45
     Mother
    0.45
     ဒီ
    0.43
     Nure
    0.43
     Cay
    0.43
     تاسو
    0.43
    Activations Density 0.000%

    No Known Activations