© 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. 188740
    Prev
    Next
    INDEX
    Explanations

    sterling silver

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

    mathematical or scientific notation

    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
    וד
    0.48
    רו
    0.47
    ༣
    0.46
    ק
    0.45
    ח
    0.44
     רו
    0.44
    ג
    0.44
    בי
    0.43
    ד
    0.43
    ן
    0.43
    POSITIVE LOGITS
     it
    0.42
     network
    0.38
     high
    0.36
     key
    0.36
     y
    0.35
     an
    0.35
     keys
    0.35
     one
    0.35
     epoxy
    0.35
     dialysis
    0.34
    Activations Density 0.005%

    No Known Activations