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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11380
    Prev
    Next
    INDEX
    Explanations

    reserves the right to

    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
     примерно
    -1.33
     兄弟
    -1.11
     TWO
    -1.09
     estamos
    -1.08
     nestled
    -1.05
     probably
    -1.05
     maybe
    -1.05
    ссии
    -1.02
    ablemente
    -1.01
    恪
    -1.01
    POSITIVE LOGITS
    НГ
    1.42
     опубли
    1.26
    choose
    1.20
     ſi
    1.18
     Ajouter
    1.18
     própri
    1.17
    however
    1.16
    選擇
    1.16
     diverses
    1.15
     unending
    1.13
    Activations Density 0.009%

    No Known Activations