© 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. 221635
    Prev
    Next
    INDEX
    Explanations

    youths and components

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

    recommended, highly recommended

    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>
    0.44
    0
    0.42
    Princeton
    0.42
    сно
    0.42
    病毒
    0.41
    优先
    0.41
    ٓ
    0.41
    Primer
    0.41
    Til
    0.41
    CCCN
    0.39
    POSITIVE LOGITS
     LiDAR
    0.50
     اك
    0.50
     uber
    0.48
     irrevoc
    0.48
     escaping
    0.48
     ܗ
    0.47
     douloureuse
    0.47
     Akad
    0.46
     Sailing
    0.46
     यात्रा
    0.46
    Activations Density 0.000%

    No Known Activations