© 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. 125412
    Prev
    Next
    INDEX
    Explanations

    Activision Blizzard, Stable Diffusion, specific entities

    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
    𝓪
    0.38
     улуч
    0.36
    充実
    0.35
     پیسې
    0.35
     භාවිත
    0.34
    améliorer
    0.34
     ఖాత
    0.34
     prosegu
    0.34
     एल्गोरि
    0.33
     अपलोड
    0.33
    POSITIVE LOGITS
    sometimes
    0.41
     sometimes
    0.37
     Sometimes
    0.36
    ↵
    0.35
     combinations
    0.34
        
    0.33
    Sometimes
    0.33
     robotics
    0.33
     اسم
    0.32
     large
    0.32
    Activations Density 0.030%

    No Known Activations