© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15751
    Prev
    Next
    INDEX
    Explanations

    opinions, advice, or statements

    np_acts-logits-general · gemini-2.5-flash-lite

    in addition to upgrading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    いております
    0.38
    ٻ
    0.37
     chy
    0.37
     perf
    0.37
    ाइल
    0.37
     reeds
    0.37
     dull
    0.36
     COS
    0.36
     ttk
    0.35
     ks
    0.35
    POSITIVE LOGITS
    <unused63>
    0.52
    enburg
    0.44
    ‬
    0.41
    ↵↵↵
    0.39
    tinger
    0.37
    }:
    0.37
    anesulfonyl
    0.36
    enstein
    0.36
     покра
    0.36
    </div>
    0.36
    Activations Density 0.192%

    No Known Activations