© 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. 88875
    Prev
    Next
    INDEX
    Explanations

    Martian environment

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

    technical terms and their context

    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
    轶
    0.55
     exemplos
    0.55
    יה
    0.53
    猢
    0.51
    ның
    0.50
    г
    0.50
    מל
    0.49
    и
    0.48
    נ
    0.48
     ის
    0.47
    POSITIVE LOGITS
     format
    0.47
     unfortunately
    0.47
     conveniently
    0.46
     complicates
    0.45
     steril
    0.45
     sexually
    0.45
     RTL
    0.45
     player
    0.45
     played
    0.44
     meet
    0.44
    Activations Density 0.000%

    No Known Activations