© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 231
    Prev
    Next
    INDEX
    Explanations

    color gold ware

    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
     ún
    1.55
     #:
    1.46
     Qualifier
    1.42
     Praha
    1.41
    Tokenizer
    1.40
     आयोग
    1.40
     đc
    1.39
    Decorator
    1.36
     الاولى
    1.36
     ako
    1.35
    POSITIVE LOGITS
    बल
    1.47
    मर्रा
    1.39
    さと
    1.39
    𝚍
    1.36
    ம்
    1.31
     şi
    1.31
    barrow
    1.30
    asText
    1.30
    ন্ত
    1.30
    Whilst
    1.29
    Activations Density 0.000%

    No Known Activations