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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13787
    Prev
    Next
    INDEX
    Explanations

    conditions and status

    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_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
    𒈪
    1.63
    𒃲
    1.62
    爣
    1.59
    𒌆
    1.57
    >)`](
    1.56
    𒀫
    1.54
     saddas
    1.52
    𒊺
    1.52
     txtbtn
    1.52
    𒆗
    1.52
    POSITIVE LOGITS
     and
    1.17
    ity
    1.12
    s
    1.05
    ness
    1.03
    ي
    0.99
    and
    0.99
    idad
    0.98
    hellip
    0.98
    ijk
    0.96
    и
    0.93
    Activations Density 0.006%

    No Known Activations