© 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. 34843
    Prev
    Next
    INDEX
    Explanations

    portable and easy to carry

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

    portable or portability

    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
    anish
    0.48
     streamlined
    0.45
    elow
    0.44
    стами
    0.43
     enlarged
    0.42
    队员
    0.41
    埃
    0.41
     rounded
    0.40
    rounded
    0.40
    败
    0.39
    POSITIVE LOGITS
     portable
    0.97
     portátil
    0.93
     Portable
    0.88
    Portable
    0.88
    portable
    0.84
     portability
    0.74
     Laptop
    0.63
     порта
    0.58
     laptop
    0.57
     이동
    0.57
    Activations Density 0.023%

    No Known Activations