© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4497
    Prev
    Next
    INDEX
    Explanations

    investment ratio

    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_12_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
     Parkland
    1.62
     Carlsbad
    1.58
    kowo
    1.56
    amarca
    1.56
     Zab
    1.56
     Palis
    1.52
     bandeja
    1.52
    播
    1.50
    摘
    1.50
     Oviedo
    1.48
    POSITIVE LOGITS
     ratio
    2.87
     Ratio
    2.62
     ratios
    2.62
    Ratio
    2.59
    ratio
    2.33
     Verhältnis
    2.08
     proportion
    1.96
     Proportion
    1.92
     proporción
    1.87
     비율
    1.79
    Activations Density 0.048%

    No Known Activations