© 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. 14413
    Prev
    Next
    INDEX
    Explanations

    R&D and M&A acronyms

    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
    ‍♀️
    2.67
    ‍♂️
    2.63
     el
    2.56
    逅
    2.49
    DETAILS
    2.49
    ngt
    2.45
    ng
    2.39
    भात
    2.35
     گے۔
    2.34
    uploads
    2.32
    POSITIVE LOGITS
    ت
    3.73
    ing
    3.30
    ের
    3.05
    onis
    2.96
    ות
    2.93
    ed
    2.82
    я
    2.74
    ateľ
    2.69
    ة
    2.58
    ات
    2.53
    Activations Density 0.006%

    No Known Activations