© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 180900
    Prev
    Next
    INDEX
    Explanations

    Oh My!

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

    sequences after specific 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
    ッド
    0.52
    法施行
    0.49
    Wert
    0.48
    ፈላ
    0.46
    Secondo
    0.45
     なる
    0.44
    踏
    0.42
    Kost
    0.42
    terminology
    0.41
    कक्ष
    0.41
    POSITIVE LOGITS
    aler
    0.47
    anda
    0.45
    irs
    0.45
    est
    0.43
    ong
    0.43
    z
    0.42
    oli
    0.41
    aria
    0.41
    alu
    0.40
     Maharashtra
    0.40
    Activations Density 0.000%

    No Known Activations