© 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. 22-GEMMASCOPE-2-RES-16K
    7. 962
    Prev
    Next
    INDEX
    Explanations

    listing or adding information

    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_22_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
    ‒
    1.72
    <unused2169>
    1.67
    ―
    1.60
    <unused2197>
    1.54
    ⁠
    1.53
    ​—
    1.53
    —
    1.49
    ־
    1.41
    ──
    1.39
    ––
    1.38
    POSITIVE LOGITS
     ppl
    2.92
     đc
    2.66
     Govt
    2.54
     IMHO
    2.46
     dgn
    2.44
     govt
    2.40
     yg
    2.33
     alot
    2.28
     dept
    2.23
     lvl
    2.18
    Activations Density 3.219%

    No Known Activations