© 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. 126143
    Prev
    Next
    INDEX
    Explanations

    ancient historical places

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

    mathematical calculations

    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
     $+\
    0.46
    AVY
    0.46
     %>
    0.42
     chứa
    0.41
    欲しい
    0.41
    ាញ់
    0.41
    ขาด
    0.41
    殺
    0.41
     đo
    0.40
    ';
    0.40
    POSITIVE LOGITS
    لین
    0.47
     affiliations
    0.45
     élément
    0.45
     affiliation
    0.45
     reimag
    0.44
     উপমহাদেশ
    0.44
     element
    0.43
     modality
    0.43
     unapolog
    0.43
     elementów
    0.43
    Activations Density 0.000%

    No Known Activations