© 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. 125791
    Prev
    Next
    INDEX
    Explanations

    unique needs

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

    words followed by specific terms

    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
     flask
    0.51
     flasks
    0.44
     x
    0.43
    ankind
    0.42
     উদ্ভ
    0.41
    不要
    0.41
     группы
    0.40
     ntawm
    0.40
     dissipative
    0.40
     dissipation
    0.40
    POSITIVE LOGITS
     getan
    0.45
    Entries
    0.43
    
    0.43
     precedents
    0.42
    𝒜
    0.42
     براي
    0.41
    ？！
    0.41
    Carta
    0.41
     بۆ
    0.40
    
    0.40
    Activations Density 0.001%

    No Known Activations