© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14623
    Prev
    Next
    INDEX
    Explanations

    we have

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

    structured lists with labels

    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_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
     parent
    0.50
    adios
    0.47
    했고
    0.46
     propensity
    0.45
    τια
    0.44
    ʋ
    0.43
     Parent
    0.42
    ²,
    0.42
    Ь
    0.42
     hub
    0.42
    POSITIVE LOGITS
    is
    0.52
    㵴
    0.49
     عربي
    0.49
     estarán
    0.48
     erhält
    0.48
    崱
    0.48
    getvalue
    0.45
     deberá
    0.45
    赋值
    0.45
     প্রাপ
    0.44
    Activations Density 0.004%

    No Known Activations