© 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. 28017
    Prev
    Next
    INDEX
    Explanations

    first public availability

    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
     Alternatives
    0.44
     Barclays
    0.39
    Alternatives
    0.39
     SAC
    0.39
     Mondays
    0.38
     alternatives
    0.37
     கூறி
    0.37
    趄
    0.37
    Simon
    0.37
     divisive
    0.37
    POSITIVE LOGITS
    物品
    0.42
     NSURL
    0.41
    Очень
    0.39
     כאשר
    0.39
     điều
    0.38
     ವಸ್ತು
    0.38
     energetics
    0.38
    یشن
    0.38
     procurar
    0.38
     একেবারেই
    0.38
    Activations Density 0.050%

    No Known Activations