© 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. 11695
    Prev
    Next
    INDEX
    Explanations

    parking areas, credit cards, specific times

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

    potential requirements and barriers

    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
    ie
    0.43
    finance
    0.41
    ad
    0.40
     लेन
    0.40
    ,​
    0.39
     riverside
    0.39
    arla
    0.39
    റി
    0.38
    ylum
    0.38
    lemon
    0.38
    POSITIVE LOGITS
     خلا
    0.42
     arrhythmias
    0.42
    发射
    0.41
     peptides
    0.40
     aumentada
    0.40
     있도록
    0.40
     ausreiche
    0.40
    挀
    0.40
    واع
    0.40
    澳大利
    0.39
    Activations Density 0.000%

    No Known Activations