© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1600
    Prev
    Next
    INDEX
    Explanations

    subprime lending or character alignment

    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_7_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
    <unused1182>
    2.90
     इम्मे
    2.79
    <unused1187>
    2.74
     strListName
    2.70
    캿
    2.65
     retShape
    2.65
     yojet
    2.64
     क़ुर्आन
    2.63
    <unused1341>
    2.63
     dissanti
    2.63
    POSITIVE LOGITS
    ia
    2.23
    to
    2.19
    of
    2.16
    he
    2.15
    I
    2.11
    we
    2.07
    th
    2.00
    no
    1.94
    they
    1.87
    ı
    1.87
    Activations Density 0.628%

    No Known Activations