© 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
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1718
    Prev
    Next
    INDEX
    Explanations

    context matters

    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
     абсолютно
    1.09
    <unused2145>
    1.06
    下記の
    1.06
     గారి
    1.05
    ಥವಾ
    1.04
    <unused284>
    1.04
    ᓲ
    1.03
    ौड़
    1.03
     vutto
    1.03
    <unused2181>
    1.02
    POSITIVE LOGITS
     regions
    0.82
     Nevertheless
    0.78
     contamination
    0.76
     The
    0.75
     separation
    0.75
    png
    0.72
     Between
    0.71
     growth
    0.68
     individuality
    0.68
     common
    0.67
    Activations Density 0.345%

    No Known Activations