© 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. 61517
    Prev
    Next
    INDEX
    Explanations

    student or person being discussed

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

    formation, segmentation, demographics

    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
     mpl
    0.50
    嬗
    0.47
     stronghold
    0.46
    柽
    0.45
     सेले
    0.44
    ен
    0.42
    altering
    0.42
    ิม
    0.41
     Kingston
    0.41
     createState
    0.40
    POSITIVE LOGITS
     échanc
    0.45
     Ông
    0.45
    đ
    0.45
    Ông
    0.45
     diretto
    0.43
     welcher
    0.43
     Ngh
    0.42
     نے
    0.41
    insurer
    0.41
    လည်း
    0.41
    Activations Density 0.000%

    No Known Activations