© 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. 73600
    Prev
    Next
    INDEX
    Explanations

    goose outlet canada, iPhone cases, cheap jewelry, replica handbags

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

    truce between or is

    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
    0.54
    <0x0D>
    0.53
     <
    0.50
    EN
    0.49
     turbine
    0.49
     beginners
    0.48
     QR
    0.47
    0
    0.47
    from
    0.47
    4
    0.47
    POSITIVE LOGITS
    结婚
    0.61
     женщина
    0.50
     नियुक्ति
    0.49
     엄마
    0.49
     vagin
    0.49
    setNome
    0.49
     Църква
    0.48
    angerschaft
    0.48
     Parenthood
    0.47
     Mommy
    0.47
    Activations Density 0.001%

    No Known Activations