© 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. 137073
    Prev
    Next
    INDEX
    Explanations

    word followed by particle

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

    phrases following pronouns and common German words

    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
     フロ
    0.55
     امکان
    0.52
     لار
    0.49
     وجود
    0.49
     چلا
    0.48
     وړاند
    0.47
     کول
    0.47
     足
    0.46
     acabou
    0.46
     همراه
    0.45
    POSITIVE LOGITS
    琏
    0.48
     Shipment
    0.46
    TextView
    0.44
    рои
    0.44
    mask
    0.43
     Generate
    0.43
    свя
    0.42
    spiration
    0.42
     lijst
    0.42
     ilişkin
    0.42
    Activations Density 0.000%

    No Known Activations