© 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. 37970
    Prev
    Next
    INDEX
    Explanations

    js followed by could

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

    html css link tag

    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
    ↵
    0.58
     Tutorials
    0.49
    <0x92>
    0.43
     fontFamily
    0.42
    ong
    0.41
    现代
    0.41
    C
    0.41
    აძ
    0.40
     myCamera
    0.40
    Exponent
    0.40
    POSITIVE LOGITS
    seud
    0.49
     alanine
    0.49
    verfahren
    0.48
    ре
    0.47
     aparato
    0.45
    orifice
    0.45
    ورہ
    0.45
    手順
    0.44
     vire
    0.44
    MainActivityTest
    0.43
    Activations Density 0.000%

    No Known Activations