© 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. 1193
    Prev
    Next
    INDEX
    Explanations

    counterpart or opposite

    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
    '।
    1.31
    」。
    1.27
    "。
    1.27
    。<
    1.25
    "!
    1.23
    ᆢ
    1.21
    ."'
    1.21
    。)
    1.21
    ”。
    1.19
    ।'
    1.17
    POSITIVE LOGITS
     (
    1.10
     also
    1.01
     conversely
    1.00
     alternatively
    0.95
     others
    0.94
     idem
    0.93
     ise
    0.93
     लागि
    0.92
    /
    0.91
     andre
    0.91
    Activations Density 3.192%

    No Known Activations