© 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. 3458
    Prev
    Next
    INDEX
    Explanations

    keywords for code inclusion and generation

    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
    Zm
    1.78
    ément
    1.75
    𝐳
    1.67
    backslash
    1.67
    unis
    1.64
     Bourke
    1.63
    ̃
    1.62
    ajn
    1.62
    ОО
    1.60
     cumpr
    1.59
    POSITIVE LOGITS
     donor
    1.46
     anodic
    1.43
     fundraisers
    1.42
    hope
    1.31
    ("/{
    1.29
     trustees
    1.29
     scholarships
    1.21
     donors
    1.20
     condemned
    1.20
    轆
    1.20
    Activations Density 0.001%

    No Known Activations