© 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. 10792
    Prev
    Next
    INDEX
    Explanations

    complex concepts

    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
     slogans
    0.48
     tweeted
    0.45
     नारेबाजी
    0.45
     liht
    0.43
     zei
    0.43
     tweets
    0.42
     secrete
    0.42
    '],'
    0.42
     chante
    0.42
     korte
    0.42
    POSITIVE LOGITS
    Complex
    0.62
    Full
    0.54
    complex
    0.53
     complex
    0.52
     Complex
    0.52
     COMPLEX
    0.51
    full
    0.50
    フル
    0.49
    Complete
    0.49
    Advanced
    0.48
    Activations Density 0.001%

    No Known Activations