© 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. 95499
    Prev
    Next
    INDEX
    Explanations

    time that

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

    conditional conjunctions

    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
    Type
    0.47
    Second
    0.43
    earth
    0.42
    용
    0.42
    ten
    0.41
    Pages
    0.41
    Style
    0.40
    Your
    0.39
    b
    0.39
    4
    0.39
    POSITIVE LOGITS
    MovementControls
    0.51
     নত
    0.47
     заявил
    0.47
     diny
    0.46
     jei
    0.46
     якщо
    0.46
    ফিকুল
    0.45
     முன்னாள்
    0.45
     если
    0.45
    する必要
    0.45
    Activations Density 0.001%

    No Known Activations