© 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. 95784
    Prev
    Next
    INDEX
    Explanations

    such such other languages

    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
     także
    -1.38
     również
    -1.29
     myös
    -1.16
     also
    -1.15
     также
    -1.13
     correct
    -1.13
    Conventional
    -1.09
     challenge
    -1.06
     imidlertid
    -1.05
     delicious
    -1.03
    POSITIVE LOGITS
     столь
    1.55
     such
    1.48
     इत
    1.40
    Such
    1.31
    这种
    1.28
    这么
    1.23
     sådan
    1.08
     Fußballspieler
    1.08
    ขนาด
    1.08
     telles
    1.08
    Activations Density 0.020%

    No Known Activations