© 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. 5936
    Prev
    Next
    INDEX
    Explanations

    your and your relationships

    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
    딪
    0.34
    飏
    0.33
    變得
    0.30
    어졌
    0.30
     thriving
    0.30
    ה
    0.30
     αποτέ
    0.29
    凭借
    0.29
    变得
    0.29
    ኘት
    0.29
    POSITIVE LOGITS
     own
    0.38
     sendiri
    0.37
     tentang
    0.33
     propias
    0.33
     propios
    0.32
     propio
    0.31
    0
    0.31
     propre
    0.30
     eigenes
    0.30
     próprio
    0.30
    Activations Density 0.097%

    No Known Activations