© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93047
    Prev
    Next
    INDEX
    Explanations

    certain examples

    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
    環境
    0.48
    ಕಾಶ
    0.47
    電源
    0.46
    ד
    0.46
    ايا
    0.46
    }=$
    0.45
    なども
    0.45
    𝚙
    0.45
    }$;
    0.44
     играет
    0.44
    POSITIVE LOGITS
     certain
    0.46
     Certain
    0.45
     sometimes
    0.45
     They
    0.44
     Mixture
    0.42
     Worldwide
    0.41
     Mixtures
    0.41
     tiered
    0.40
     tertentu
    0.39
     Sometimes
    0.38
    Activations Density 0.005%

    No Known Activations