© 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. 248840
    Prev
    Next
    INDEX
    Explanations

    with regards to

    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
     produtt
    0.47
    גו
    0.46
     restful
    0.44
    ภายใน
    0.44
     negozio
    0.44
     singoli
    0.44
     premio
    0.43
    )}}{
    0.43
     partite
    0.43
     conseguir
    0.43
    POSITIVE LOGITS
    ссии
    0.52
    ब्दी
    0.51
    olphin
    0.45
    ర్చి
    0.43
    Ι
    0.42
    ﾝ
    0.42
    Ду
    0.42
    ণে
    0.41
     Mathematical
    0.41
    nonce
    0.41
    Activations Density 0.000%

    No Known Activations