© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 550
    Prev
    Next
    INDEX
    Explanations

    approximationsabout percentages or ranges

    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
    𝒸
    1.93
    േക്ക്
    1.84
    جواب
    1.79
    zerű
    1.78
    ীক
    1.75
    ليس
    1.74
    TTLE
    1.71
    اپ
    1.68
     brach
    1.66
     vijj
    1.65
    POSITIVE LOGITS
    ਹ
    1.86
    pling
    1.83
    ]".
    1.72
     League
    1.71
    不及
    1.70
    pied
    1.69
    pton
    1.68
    Ant
    1.67
     ".$
    1.65
    入
    1.63
    Activations Density 0.546%

    No Known Activations