© 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. 20179
    Prev
    Next
    INDEX
    Explanations

    punctuation before phrases

    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
     permanece
    0.52
    asilkan
    0.44
     एडिशन
    0.44
     councillor
    0.43
     troca
    0.41
     pembayaran
    0.40
     ス
    0.40
     cielo
    0.40
    <unused10>
    0.40
    <unused90>
    0.40
    POSITIVE LOGITS
    ၊
    0.43
     Rainer
    0.42
    $,
    0.41
     Werner
    0.41
     Vern
    0.41
    .$\
    0.38
    ،
    0.38
     Rauch
    0.38
    EL
    0.38
    ፣
    0.38
    Activations Density 0.015%

    No Known Activations