© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 437
    Prev
    Next
    INDEX
    Explanations

    applying or seeing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     ello
    1.45
     Rien
    1.44
     mirada
    1.43
    </blockquote>
    1.41
     guerra
    1.41
     questo
    1.40
     danza
    1.39
     verticale
    1.39
     guerras
    1.38
     dédi
    1.37
    POSITIVE LOGITS
    使用
    1.57
    使用的是
    1.41
    岨
    1.40
     χρησιμοποι
    1.37
    奈川
    1.34
    使用的
    1.33
     lawfully
    1.30
    携带
    1.30
    eft
    1.28
    encrypted
    1.28
    Activations Density 0.000%

    No Known Activations