© 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. 6607
    Prev
    Next
    INDEX
    Explanations

    rule-based

    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
    เคราะห์
    1.85
     карда
    1.80
    платно
    1.74
    }^{*}
    1.73
     BONUS
    1.64
    pcion
    1.62
    ặng
    1.60
    坞
    1.60
     baat
    1.58
    プション
    1.56
    POSITIVE LOGITS
    setting
    2.24
     setters
    2.06
    Setter
    2.03
    set
    1.90
    setter
    1.89
    high
    1.81
     setter
    1.79
    breakers
    1.78
    Set
    1.78
     breakers
    1.72
    Activations Density 0.084%

    No Known Activations