© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15025
    Prev
    Next
    INDEX
    Explanations

    starting words for specific entities

    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
     потребуется
    -1.32
     понадобится
    -1.23
     ebenso
    -1.20
     هذه
    -1.19
    SONY
    -1.13
    従来
    -1.09
    SAD
    -1.08
    STALK
    -1.08
    ignored
    -1.07
     latina
    -1.06
    POSITIVE LOGITS
     overall
    1.42
     general
    1.35
    がとても
    1.28
     which
    1.22
    ーーーー
    1.18
     tecnologie
    1.16
    好像是
    1.15
     macchine
    1.15
    hecho
    1.14
     risorse
    1.13
    Activations Density 0.001%

    No Known Activations