© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 60319
    Prev
    Next
    INDEX
    Explanations

    unique identity

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

    closing punctuation or delimiters

    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
    ه
    0.49
    б
    0.48
    و
    0.47
    ো
    0.46
    د
    0.46
    ومان
    0.45
    Lev
    0.44
    ب
    0.44
    ोरा
    0.43
    ル
    0.43
    POSITIVE LOGITS
     CLEAN
    0.50
     SECURITY
    0.45
     DECIMAL
    0.45
    )}
    0.43
    र्वाद
    0.43
     Dumas
    0.43
    rimidin
    0.43
     PRODU
    0.42
     Dose
    0.41
    REFERENCE
    0.41
    Activations Density 0.000%

    No Known Activations