© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75071
    Prev
    Next
    INDEX
    Explanations

    Vascularized, Five Things, Roxanne

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ''');
    -1.23
    śred
    -1.23
    ERICA
    -1.07
    cestors
    -1.05
    ≦
    -1.04
     Romains
    -1.02
    nalité
    -1.01
    meja
    -1.01
     menn
    -1.01
    𝟭
    -1.00
    POSITIVE LOGITS
     and
    1.14
    最后的
    1.13
    zten
    0.93
     phobia
    0.92
     berbagai
    0.92
    不愿
    0.92
    最後は
    0.91
     último
    0.90
     vile
    0.90
     rebaj
    0.88
    Activations Density 0.000%

    No Known Activations