© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5600
    Prev
    Next
    INDEX
    Explanations

    words ending in 's' or 'bs'

    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
    h
    2.07
    tı
    1.98
    hap
    1.95
    lə
    1.95
    dio
    1.95
    hiv
    1.91
    tac
    1.85
    tin
    1.84
    hv
    1.84
    t
    1.84
    POSITIVE LOGITS
    ذه
    1.76
    ensed
    1.67
    projectlombok
    1.66
    轭
    1.65
    ędzy
    1.64
    ция
    1.61
    arsko
    1.60
    циями
    1.60
    addView
    1.59
    quartered
    1.58
    Activations Density 0.309%

    No Known Activations