© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12615
    Prev
    Next
    INDEX
    Explanations

    pm or operation

    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
    ை
    2.23
    ి
    2.19
    fficient
    2.03
    ைச்
    2.00
    వా
    1.99
    े
    1.98
    ைக்கு
    1.97
    bayes
    1.94
    resolver
    1.94
    apolitan
    1.93
    POSITIVE LOGITS
    𝐡
    2.69
    𝐚
    2.58
    𝐢
    2.45
    𝐬
    2.37
    𝐨
    2.22
    ็จ
    2.19
    𝐛
    2.15
    ynchronously
    2.14
    </a>
    2.10
    𝓲
    2.08
    Activations Density 0.013%

    No Known Activations