© 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. 50958
    Prev
    Next
    INDEX
    Explanations

    San Francisco

    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
    et
    0.49
     brothers
    0.46
     Trends
    0.44
     Przed
    0.44
    国的
    0.43
     夏
    0.43
     philosophy
    0.43
    య
    0.43
     Proof
    0.42
     Summer
    0.41
    POSITIVE LOGITS
    май
    0.51
    butan
    0.49
    нит
    0.46
     கீழ்
    0.46
    itemBackground
    0.46
     ።
    0.45
    मोह
    0.44
    ganggu
    0.44
    пта
    0.44
    бут
    0.44
    Activations Density 0.002%

    No Known Activations