© 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. 45364
    Prev
    Next
    INDEX
    Explanations

    common words before specific terms

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

    process, SLR, children, they achieve

    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
    殁
    0.49
    奥运
    0.46
     важно
    0.45
    踽
    0.45
     মেসির
    0.43
     ebben
    0.43
     quizás
    0.43
    ~!
    0.42
     Ángel
    0.42
    应该
    0.42
    POSITIVE LOGITS
    sht
    0.47
    ុំ
    0.46
    indeterminate
    0.46
    adir
    0.46
    anfa
    0.44
    fire
    0.43
     ਜਾਂ
    0.43
    facebook
    0.43
    ship
    0.41
    Interstitial
    0.41
    Activations Density 0.000%

    No Known Activations