© 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. 18024
    Prev
    Next
    INDEX
    Explanations

    testing beginners space issue Dr

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

    reduces glucose

    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
    <0x80>
    0.50
    <0xBA>
    0.50
    仕上げ
    0.45
     vers
    0.45
    <0x99>
    0.44
    كال
    0.43
    <0xBF>
    0.43
    sten
    0.43
    。)
    0.42
    versa
    0.41
    POSITIVE LOGITS
    হয়
    0.51
    লস
    0.50
    resent
    0.50
     pathogenicity
    0.49
     Sequences
    0.48
     detergents
    0.47
    𝙔
    0.47
     करिएगा
    0.47
     litres
    0.47
     Toxicity
    0.46
    Activations Density 0.000%

    No Known Activations