© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13320
    Prev
    Next
    INDEX
    Explanations

    MLOps platform and frameworks

    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
     Айдз
    3.34
    𒈹
    3.23
    𒌜
    3.21
     Рассмотрим
    3.21
    𒊌
    3.21
    𒋑
    3.19
    𒈣
    3.18
    𒀌
    3.18
    <unused1442>
    3.18
    ꗏ
    3.18
    POSITIVE LOGITS
    n
    2.84
    es
    2.43
    り
    2.31
    “
    2.17
    t
    2.15
    en
    2.13
    te
    2.11
    se
    2.11
    r
    2.11
    sum
    2.09
    Activations Density 0.005%

    No Known Activations