© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2545
    Prev
    Next
    INDEX
    Explanations

    initial potential concepts behavior maximum

    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_65k_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
    м
    2.34
    er
    2.32
    ing
    2.27
    e
    2.19
    т
    2.18
    y
    2.18
    ה
    2.17
    the
    2.15
    ed
    2.15
    д
    2.13
    POSITIVE LOGITS
     finest
    2.05
     rendition
    2.04
     brightest
    1.92
     roadmap
    1.88
     sake
    1.83
     Sake
    1.80
     newest
    1.79
     fifteenth
    1.79
     fourteenth
    1.79
     vacated
    1.79
    Activations Density 0.355%

    No Known Activations