© 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. 2405
    Prev
    Next
    INDEX
    Explanations

    authentication / tasks / errors

    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
    
    2.02
    >**
    1.94
    ׃
    1.89
     tenor
    1.87
    หน่วย
    1.85
    loy
    1.84
    
    1.83
    stmt
    1.82
    ine
    1.82
     rés
    1.81
    POSITIVE LOGITS
     socalled
    0.80
    шибка
    0.69
     unrecognized
    0.67
    ВД
    0.65
    مار
    0.65
     forgetting
    0.64
    forget
    0.63
    能不能
    0.62
    賤
    0.61
    Unable
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.