© 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. 67441
    Prev
    Next
    INDEX
    Explanations

    wise and

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

    protecting animal life

    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
    entraî
    0.47
    或者
    0.45
     convincingly
    0.45
    ή
    0.43
     või
    0.43
     Krankheit
    0.42
    病情
    0.41
     அல்லது
    0.40
    皮肤
    0.40
    巉
    0.40
    POSITIVE LOGITS
    なのに
    0.49
     udah
    0.47
     лабора
    0.44
     sanctity
    0.43
     museums
    0.43
     infrastructure
    0.43
     innovators
    0.42
     infrastructures
    0.42
     ambience
    0.41
     scanners
    0.41
    Activations Density 0.001%

    No Known Activations