© 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. 3166
    Prev
    Next
    INDEX
    Explanations

    Former MP

    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
    
    0.28
    🗯
    0.26
     %``
    0.24
     titleImageUrl
    0.23
     conteú
    0.22
     sbParams
    0.22
    Methylsulfanyl
    0.21
    ⏺
    0.21
    味が
    0.21
     ſh
    0.21
    POSITIVE LOGITS
     
    0.40
     I
    0.34
    k
    0.29
    st
    0.29
    i
    0.28
     it
    0.27
     to
    0.26
    y
    0.25
     be
    0.25
     A
    0.25
    Activations Density 1.312%

    No Known Activations