© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1487
    Prev
    Next
    INDEX
    Explanations

    years and centuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    <bos>
    2.71
    قه
    2.57
    spielen
    2.54
    ट
    2.48
    𝒎
    2.46
    टू
    2.43
    vidas
    2.41
    rator
    2.39
    Bbb
    2.38
    rennen
    2.35
    POSITIVE LOGITS
    er
    2.83
    )‏
    2.51
    。」
    2.40
     '../../../
    2.40
    বীন্দ্রনাথ
    2.39
    eris
    2.35
    थमिक
    2.34
    ष्‍ट्र
    2.34
     vort
    2.27
    ும்
    2.25
    Activations Density 0.433%

    No Known Activations