© 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. 169830
    Prev
    Next
    INDEX
    Explanations

    light chain

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

    keywords for technical/formal topics

    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
    禳
    0.51
    тся
    0.50
    dogan
    0.49
    ないので
    0.47
    کو
    0.46
    azar
    0.45
    സ്ഥ
    0.45
     yoki
    0.45
    dollar
    0.45
    ică
    0.44
    POSITIVE LOGITS
     其中
    0.49
     구분
    0.48
     말했다
    0.47
     jednu
    0.47
     入
    0.47
     avid
    0.46
     niacin
    0.46
     qRT
    0.45
     MeOH
    0.44
     如
    0.44
    Activations Density 0.001%

    No Known Activations