© 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. 91619
    Prev
    Next
    INDEX
    Explanations

    linking to what follows

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

    smaller, competition, development

    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
    aka
    0.53
    ep
    0.52
    arr
    0.51
     promised
    0.50
     mand
    0.50
    ala
    0.49
    E
    0.47
    au
    0.47
     ét
    0.46
     resent
    0.46
    POSITIVE LOGITS
    cuando
    0.49
    𝗌
    0.48
     dwRes
    0.48
    當
    0.47
     innovators
    0.47
     রাইফ
    0.46
     হন্ড
    0.44
    撣
    0.44
    埥
    0.44
    ueta
    0.44
    Activations Density 0.000%

    No Known Activations