© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3046
    Prev
    Next
    INDEX
    Explanations

    having trouble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    即可
    1.40
    ,":
    1.28
    othed
    1.26
    áculo
    1.25
    』（
    1.23
    」（
    1.23
    rupulous
    1.22
     */;
    1.20
     prescriptive
    1.18
    >-</
    1.17
    POSITIVE LOGITS
     sooo
    1.72
     soooo
    1.70
    such
    1.66
    пи
    1.60
     soo
    1.59
     beberapa
    1.58
     some
    1.58
     SUCH
    1.57
     بعض
    1.57
     таких
    1.56
    Activations Density 0.274%

    No Known Activations