© 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. 967
    Prev
    Next
    INDEX
    Explanations

    php code and real-world data

    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
     anticon
    1.16
     atlet
    1.14
     geno
    1.14
    лень
    1.13
     anlay
    1.12
    otyping
    1.12
    irati
    1.11
    惰
    1.11
    legraf
    1.08
    onya
    1.08
    POSITIVE LOGITS
    陥
    1.00
    QRSTUVWXYZ
    0.88
    ʂ
    0.83
    Thrown
    0.83
    })}$
    0.82
    営業
    0.81
    Unlock
    0.81
    venida
    0.79
    smtb
    0.78
     flap
    0.77
    Activations Density 0.513%

    No Known Activations