© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6064
    Prev
    Next
    INDEX
    Explanations

    Andrew Ng, samoyed, Samothrace, misunderstanding

    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
    嬗
    1.42
    msız
    1.37
     karane
    1.34
     recensement
    1.31
    篤
    1.31
    antiti
    1.30
     elección
    1.29
     aceptación
    1.28
    icias
    1.26
    modifiable
    1.25
    POSITIVE LOGITS
    hong
    1.50
     سنی
    1.17
    िश
    1.16
    きの
    1.13
    גיע
    1.11
     Really
    1.11
    taught
    1.10
     ș
    1.08
    song
    1.08
     kaha
    1.08
    Activations Density 0.079%

    No Known Activations