© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201958
    Prev
    Next
    INDEX
    Explanations

    academic citations and technical references

    np_acts-logits-general · gemini-2.5-flash-lite

    ```python datetime```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    hitth
    0.48
     नु
    0.46
     NaCl
    0.45
     interviews
    0.45
     กิน
    0.43
    ’
    0.43
    กิน
    0.43
     ഇത്തരം
    0.43
     ज्
    0.43
     musician
    0.42
    POSITIVE LOGITS
    {
    0.39
     انقلاب
    0.37
    秘密
    0.36
    Alternatively
    0.36
    震
    0.36
     Sección
    0.35
     bölüm
    0.34
    ertos
    0.34
    рем
    0.34
    Transformer
    0.34
    Activations Density 0.000%

    No Known Activations