© 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. 16764
    Prev
    Next
    INDEX
    Explanations

    links and references

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

    AI followed by disclaimer

    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
    ي
    0.50
     მიმოწერა
    0.49
    ა
    0.49
    ת
    0.46
    ه
    0.46
    ॉल
    0.45
    來越
    0.45
    들도
    0.44
    ޟ
    0.44
    मेंट
    0.43
    POSITIVE LOGITS
     in
    0.50
     for
    0.49
    ier
    0.49
     as
    0.46
    ifying
    0.45
    iness
    0.45
    ile
    0.44
    ren
    0.44
    ning
    0.43
    ulating
    0.42
    Activations Density 0.009%

    No Known Activations