© 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-16K
    7. 3552
    Prev
    Next
    INDEX
    Explanations

    at least

    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_16k_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
     발생
    0.38
     خواہ
    0.37
     ginger
    0.37
    velden
    0.36
    }&
    0.35
     बावजूद
    0.35
     अतः
    0.34
     deoarece
    0.34
    }\\
    0.34
     совершен
    0.34
    POSITIVE LOGITS
     certainly
    0.41
     Certainly
    0.41
    少なくとも
    0.39
     differently
    0.39
    まあ
    0.38
     रुच
    0.38
    Certainly
    0.37
     atleast
    0.35
    iego
    0.35
     অন্তত
    0.34
    Activations Density 0.303%

    No Known Activations