© 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-16K
    7. 9537
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    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
    quoise
    1.76
    ifix
    1.41
    broke
    1.37
    askets
    1.35
    Phil
    1.35
    rescence
    1.34
    zil
    1.33
    堊
    1.31
    terer
    1.30
    phon
    1.23
    POSITIVE LOGITS
     hormon
    2.13
     Hormone
    1.94
     hormone
    1.89
     estrogen
    1.88
     hormones
    1.84
    激素
    1.75
     FSH
    1.74
     हार्मोन
    1.72
     Horm
    1.71
     agonist
    1.64
    Activations Density 0.112%

    No Known Activations