© 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. 80997
    Prev
    Next
    INDEX
    Explanations

    Entities, surgery, or numbering

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

    instructions for formatting

    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
     މ
    0.47
    ↵↵↵↵
    0.46
    ↵↵↵↵↵
    0.46
    ↵
    0.45
     மற்றும்
    0.43
    ת
    0.42
    ी
    0.42
    า
    0.41
     মজার
    0.41
     அது
    0.40
    POSITIVE LOGITS
     tuf
    0.42
    ᾷ
    0.42
    ंबर्स
    0.39
     fraî
    0.39
    ≳
    0.39
     είναι
    0.39
     centrifuged
    0.39
    сных
    0.38
     przys
    0.38
    aneers
    0.37
    Activations Density 0.000%

    No Known Activations