© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 12347
    Prev
    Next
    INDEX
    Explanations

    startup and boot processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    1.15
     for
    1.04
     with
    1.02
     during
    0.96
     when
    0.95
    .
    0.95
     (
    0.94
     by
    0.93
     from
    0.92
     as
    0.89
    POSITIVE LOGITS
    <unused2174>
    1.20
    <unused2167>
    1.12
    茈
    1.12
    <unused1480>
    1.12
    𒆗
    1.11
    <unused1346>
    1.11
    ConfigureArg
    1.09
    navigationLinks
    1.08
    <unused2217>
    1.08
    <unused1411>
    1.07
    Activations Density 0.000%

    No Known Activations