© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 28063
    Prev
    Next
    INDEX
    Explanations

    information is physical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SERVIDOR
    0.44
    .",[
    0.44
    কেলে
    0.43
     پیسې
    0.43
    তিক্রম
    0.43
     ยาก
    0.43
     グッチ
    0.43
     सहमति
    0.42
     வால்பேப்பர்
    0.42
    𝓃
    0.42
    POSITIVE LOGITS
     Art
    0.55
     temperature
    0.50
     temperatures
    0.49
     Ivan
    0.49
     Neuron
    0.49
    4
    0.49
     Architects
    0.48
    ی
    0.48
     Matthew
    0.48
     Enzymes
    0.48
    Activations Density 0.011%

    No Known Activations