© 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. 61324
    Prev
    Next
    INDEX
    Explanations

    an NZ group alpha

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

    each should coverstandards for vehiclesinvestigation the plot

    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
    izado
    0.44
    ਅ
    0.41
     fixation
    0.41
    yun
    0.40
    locationY
    0.39
    life
    0.39
    family
    0.39
     coexistence
    0.39
    ingredient
    0.38
    ità
    0.38
    POSITIVE LOGITS
     respectively
    0.47
     போக்குவர
    0.46
     kamar
    0.45
     seeking
    0.45
     Seeking
    0.45
    镟
    0.44
    それぞれ
    0.44
    行為
    0.44
     Slovens
    0.43
     Urugu
    0.42
    Activations Density 0.000%

    No Known Activations