© 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. 56787
    Prev
    Next
    INDEX
    Explanations

    questions and whether

    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
     approximates
    0.44
    凱
    0.41
     شي
    0.40
     rope
    0.40
    <unused2173>
    0.39
     ديال
    0.39
     діа
    0.38
     hebt
    0.38
    Ε
    0.38
     διά
    0.37
    POSITIVE LOGITS
     question
    0.84
     Whether
    0.81
     wondered
    0.80
     вопрос
    0.79
     pitanje
    0.78
    Whether
    0.78
     whether
    0.76
     wondering
    0.76
     apakah
    0.76
    whether
    0.75
    Activations Density 0.099%

    No Known Activations