© 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. 204614
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases or objective clauses

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

    articles, lists, or enumerations

    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
     &
    0.57
     NIST
    0.48
     RTI
    0.46
    us
    0.45
     IPCC
    0.44
    )–
    0.44
    g
    0.44
    ms
    0.42
     )
    0.42
     LEON
    0.42
    POSITIVE LOGITS
     شرطونه
    0.51
    edì
    0.48
     thửa
    0.48
     calcule
    0.47
    マッチ
    0.46
    นาด
    0.46
     évalu
    0.46
    LiveData
    0.46
    埸
    0.46
     onders
    0.46
    Activations Density 0.001%

    No Known Activations