© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7587
    Prev
    Next
    INDEX
    Explanations

    override annotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ם
    0.98
    nál
    0.96
    י
    0.94
    AL
    0.94
    nél
    0.93
    нің
    0.91
    ER
    0.91
    ত
    0.90
    м
    0.89
    νε
    0.84
    POSITIVE LOGITS
    )]:
    0.88
    )\|_{\
    0.87
     destinée
    0.87
    ⅾ
    0.85
     hergestellt
    0.84
     जलाश
    0.84
     furnishes
    0.82
     aumentado
    0.82
    iene
    0.82
    getColumnIndex
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.