© 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. 17147
    Prev
    Next
    INDEX
    Explanations

    paragraph focuses

    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
    צ
    0.48
    מ
    0.47
    তর
    0.46
    ட்டிக்க
    0.46
    私の
    0.45
     ውጤ
    0.44
     ہے۔
    0.44
    À
    0.44
    à
    0.43
    私が
    0.43
    POSITIVE LOGITS
     ЕС
    0.44
    留
    0.44
    ංග
    0.43
     Dray
    0.43
     अश
    0.43
     आलो
    0.42
     nano
    0.42
    Signals
    0.41
     signal
    0.41
     Limitations
    0.41
    Activations Density 0.025%

    No Known Activations