© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 12721
    Prev
    Next
    INDEX
    Explanations

    teamviewer and installations

    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
     magnétique
    0.47
    ictions
    0.46
    돕
    0.45
    élect
    0.43
     réussite
    0.42
    én
    0.42
    íny
    0.41
    ict
    0.41
    apé
    0.41
     conduite
    0.40
    POSITIVE LOGITS
     as
    0.47
     sonucu
    0.46
     ఇ
    0.46
     (#
    0.46
     misinterpreted
    0.45
     తో
    0.44
    RegistrationBean
    0.43
     abrog
    0.43
     Aqu
    0.43
    ვით
    0.42
    Activations Density 0.007%

    No Known Activations