© 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. 206895
    Prev
    Next
    INDEX
    Explanations

    loss, clients, bridge, effective

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

    Midjourney

    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
     Gesture
    0.52
     hool
    0.51
    꺽
    0.49
    nivers
    0.48
    gesture
    0.46
    endor
    0.44
    ಗೊಂಡ
    0.44
    পাশ
    0.44
    holi
    0.44
    OLE
    0.44
    POSITIVE LOGITS
    to
    0.52
    р
    0.52
     белару
    0.49
     to
    0.47
    ...")
    0.47
     én
    0.47
     песен
    0.45
    îte
    0.44
     composée
    0.44
    itectura
    0.44
    Activations Density 0.000%

    No Known Activations