© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 604
    Prev
    Next
    INDEX
    Explanations

    dilapidated hut, antique maps, grizzled fisherman

    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_13_width_65k_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
    glightbox
    1.64
     vattum
    1.61
    <unused298>
    1.61
    Ngoài
    1.60
    <unused96>
    1.57
    Selain
    1.56
    <unused801>
    1.56
    <unused1248>
    1.54
    ங்களை
    1.53
    <unused860>
    1.52
    POSITIVE LOGITS
    ).
    1.50
    /
    1.47
     /
    1.45
    ,
    1.34
    );
    1.32
    )
    1.30
    :
    1.30
    ):
    1.27
    ),
    1.26
    )/
    1.26
    Activations Density 1.213%

    No Known Activations