© 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. 128946
    Prev
    Next
    INDEX
    Explanations

    Sustainable development scenarios

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

    Movie Night: Classic!

    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
    är
    0.46
     interruption
    0.44
     crowdfunding
    0.44
    🔥🔥
    0.44
     blockchain
    0.44
    椀
    0.43
     betrayal
    0.42
     forefathers
    0.42
    rtl
    0.42
     النفس
    0.42
    POSITIVE LOGITS
    뎐
    0.49
    iencia
    0.46
    גיע
    0.46
    байд
    0.46
     Lleg
    0.46
    igated
    0.45
     লাগছে
    0.44
    飫
    0.44
    Generic
    0.44
    ন্ট
    0.43
    Activations Density 0.001%

    No Known Activations