© 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-262K
    7. 26924
    Prev
    Next
    INDEX
    Explanations

    digital natives

    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_262k_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
     out
    0.51
    오
    0.45
     up
    0.44
    OP
    0.44
     primes
    0.44
    G
    0.43
     collars
    0.43
    RY
    0.43
    O
    0.42
    品
    0.42
    POSITIVE LOGITS
     क्योंकि
    0.48
     sincerity
    0.47
     कारण
    0.47
     दुष्प्रभाव
    0.45
    存档备份
    0.44
     പ്രതിഷേധ
    0.44
    ະລ
    0.43
     электронной
    0.43
    ភាគ
    0.42
     เนื่องจาก
    0.42
    Activations Density 0.002%

    No Known Activations