© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10242
    Prev
    Next
    INDEX
    Explanations

    the os module

    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
    Bechyné
    1.82
    PropertyParam
    1.73
    AgentError
    1.71
    બ
    1.70
    PTMR
    1.68
    Abasis
    1.68
    ہائی
    1.66
    ScriptBuf
    1.66
    <unused1394>
    1.65
    قة
    1.65
    POSITIVE LOGITS
    1.00
    id
    0.98
     un
    0.92
     sal
    0.89
     id
    0.87
    sum
    0.87
     sum
    0.85
     design
    0.85
    mal
    0.82
    ↵
    0.81
    Activations Density 0.001%

    No Known Activations