© 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. 7-GEMMASCOPE-2-RES-16K
    7. 121
    Prev
    Next
    INDEX
    Explanations

    JSON metadata retrieval

    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_7_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
    𝑒
    2.17
    ᴇ
    2.13
    𝑠
    2.08
    𝑡
    1.99
    𝑛
    1.96
    𝑟
    1.92
    𝑣
    1.89
    𝑔
    1.86
    endswith
    1.85
    sthresh
    1.85
    POSITIVE LOGITS
     tais
    1.74
    For
    1.67
    ક્ટર
    1.59
    Whether
    1.55
     Circ
    1.55
    c
    1.49
    為
    1.49
     vyt
    1.49
    นู
    1.48
     For
    1.47
    Activations Density 4.380%

    No Known Activations