© 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. 14140
    Prev
    Next
    INDEX
    Explanations

    high- performance descriptors

    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
    ה
    2.11
    a
    2.02
    scorer
    1.93
    s
    1.92
    e
    1.90
    ्टर
    1.88
    immer
    1.82
    ަނ
    1.81
     prognosis
    1.81
     Provident
    1.81
    POSITIVE LOGITS
    дно
    2.17
     ngôn
    2.12
     Displaystyle
    2.07
    tral
    2.05
    ﻭ
    1.99
     nửa
    1.96
    ક્ત
    1.91
    ża
    1.91
    ਨੀ
    1.88
     voert
    1.87
    Activations Density 0.018%

    No Known Activations