© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1746
    Prev
    Next
    INDEX
    Explanations

    comment markers `#` and `//`

    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_17_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
    ｣
    1.40
    」。
    1.33
    』
    1.28
    」、
    1.27
    」，
    1.25
    </td>
    1.22
    »،
    1.21
    》。
    1.19
    ”。
    1.19
    》，
    1.18
    POSITIVE LOGITS
    these
    1.29
    THIS
    1.25
    this
    1.21
    some
    1.17
     TODO
    1.17
     THIS
    1.14
     these
    1.14
    一定要
    1.11
     এটা
    1.11
     some
    1.09
    Activations Density 0.029%

    No Known Activations