© 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. 2128
    Prev
    Next
    INDEX
    Explanations

    moon and lunar references

    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
    ائی
    2.48
    ၠ
    2.46
    iophorus
    2.42
    ी
    2.41
    ไซต์
    2.40
    ம்
    2.34
    ्हे
    2.33
    BA
    2.30
    𝒋
    2.26
     jos
    2.22
    POSITIVE LOGITS
    곽
    2.80
    ఫీ
    2.67
    髏
    2.63
    iet
    2.46
     setLoading
    2.43
    ১৪
    2.41
    umballMachine
    2.40
    ens
    2.38
     ContentValues
    2.37
    鐩
    2.37
    Activations Density 0.321%

    No Known Activations