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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211294
    Prev
    Next
    INDEX
    Explanations

    printing or digital versions

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

    ```html**`item`:**```

    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_262k_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
    рма
    0.47
    ␥
    0.46
     bedrijven
    0.44
    こともある
    0.44
    uleux
    0.43
     أص
    0.43
    ídas
    0.43
     λα
    0.43
    ම්
    0.42
    غات
    0.42
    POSITIVE LOGITS
    l
    0.49
     usages
    0.43
    equilibrium
    0.42
    Sis
    0.42
    of
    0.42
    sis
    0.42
    0.42
    eszcze
    0.41
    OF
    0.41
    akhir
    0.40
    Activations Density 0.001%

    No Known Activations