© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3041
    Prev
    Next
    INDEX
    Explanations

    What does "X" mean?

    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
    ી
    3.31
    ০
    3.29
    ம்
    3.21
    ে
    3.21
    ો
    3.16
    ς
    3.14
    에
    3.10
    es
    2.89
    ۰
    2.88
    י
    2.86
    POSITIVE LOGITS
    apest
    2.57
    𝘺
    2.55
    𝘵
    2.30
     jaanu
    2.27
    ປີ
    2.17
    expiry
    2.14
    ാര്യ
    2.13
    ത്
    2.12
     malas
    2.08
     expiry
    2.04
    Activations Density 0.018%

    No Known Activations