© 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. 84332
    Prev
    Next
    INDEX
    Explanations

    or, and, also

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

    also known as

    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
    шня
    0.46
    )>
    0.43
    Broadcast
    0.43
     propagating
    0.43
    ↵
    0.43
    ten
    0.43
    propag
    0.42
    c
    0.41
    sle
    0.41
    ts
    0.41
    POSITIVE LOGITS
     அல்லது
    0.54
     ܠ
    0.50
     അല്ലെങ്കിൽ
    0.49
     صہی
    0.49
     അല്ല
    0.48
     आल्सो
    0.48
     اینڈ
    0.48
    
    0.47
     Söz
    0.46
     alemão
    0.45
    Activations Density 0.001%

    No Known Activations