© 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. 15006
    Prev
    Next
    INDEX
    Explanations

    introducing breakdowns for clarity

    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
    ்சி
    2.59
    heb
    2.58
    ｽ
    2.50
    с
    2.49
    टीआई
    2.46
    žič
    2.43
    С
    2.41
    Ру
    2.35
    ис
    2.34
    М
    2.32
    POSITIVE LOGITS
    t
    3.04
     ويكيميديا
    2.74
    tter
    2.64
    ng
    2.64
    lard
    2.61
    tags
    2.52
    tend
    2.50
    mals
    2.47
    น
    2.46
    friends
    2.41
    Activations Density 0.023%

    No Known Activations