© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 76862
    Prev
    Next
    INDEX
    Explanations

    reverting, avoiding, accumulating

    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
     cỏ
    0.51
     சிலர்
    0.49
    咀
    0.49
    ቂ
    0.48
    ంలో
    0.47
     Мини
    0.47
     наша
    0.47
     మంది
    0.47
    廨
    0.47
     Ше
    0.46
    POSITIVE LOGITS
     whilst
    0.49
     inlets
    0.48
     braking
    0.47
     climbing
    0.47
     nautical
    0.46
     aqu
    0.46
     maritime
    0.46
     pertaining
    0.46
     surfing
    0.45
     temperature
    0.44
    Activations Density 0.009%

    No Known Activations