© 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. 9319
    Prev
    Next
    INDEX
    Explanations

    command line execution

    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
    iš
    2.18
     falls
    2.09
    respect
    2.03
    ing
    1.98
    시아
    1.96
     mis
    1.95
    ت
    1.91
    erit
    1.91
    賁
    1.86
    pods
    1.84
    POSITIVE LOGITS
    __(/*!
    2.80
    chés
    2.74
    賬
    2.63
    бек
    2.61
    pherd
    2.60
    瘩
    2.59
    账
    2.58
    ഗീയ
    2.49
     製
    2.49
    logne
    2.49
    Activations Density 0.303%

    No Known Activations