© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 196342
    Prev
    Next
    INDEX
    Explanations

    foreign and other languages

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

    significant barriers and warnings

    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
    −
    0.48
    essoas
    0.47
    Nome
    0.46
    Breaking
    0.44
    ※
    0.44
    布
    0.43
    公布
    0.42
    以下
    0.42
    etera
    0.42
     中
    0.42
    POSITIVE LOGITS
     waxes
    0.55
     toujours
    0.53
     dovrebbe
    0.52
     deux
    0.48
     siempre
    0.48
     altijd
    0.48
     dulces
    0.47
     devrait
    0.47
     beaucoup
    0.47
     demasi
    0.47
    Activations Density 0.001%

    No Known Activations