© 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. 186619
    Prev
    Next
    INDEX
    Explanations

    win for, without installation, unmarried child

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

    rooted in / delivered over / acquired

    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
     apes
    0.47
     trafic
    0.45
     तस्करी
    0.45
    は大
    0.44
     пост
    0.44
     zainteres
    0.44
     -"
    0.44
    (")
    0.44
    𝚙
    0.43
    
    0.43
    POSITIVE LOGITS
    offsetHeight
    0.49
    ವಾಗಿರುತ್ತದೆ
    0.47
     باوجود
    0.46
    rosso
    0.43
     millones
    0.42
    nb
    0.42
    개가
    0.42
    DURATION
    0.41
    yb
    0.40
    adil
    0.40
    Activations Density 0.000%

    No Known Activations