© 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. 95825
    Prev
    Next
    INDEX
    Explanations

    partnered, rolled, spouse, may, caused

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

    Storage, load, survive, belong

    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
     ayatan
    0.64
     vitth
    0.48
     šest
    0.47
     Crore
    0.47
     châ
    0.46
    <unused483>
    0.46
     Dalit
    0.45
     zatím
    0.45
     nirv
    0.44
    ச்சத்து
    0.44
    POSITIVE LOGITS
    Page
    0.47
    ain
    0.44
    い
    0.44
    ial
    0.44
    nae
    0.44
    ज
    0.44
    le
    0.43
     l
    0.43
    Gra
    0.43
    n
    0.42
    Activations Density 0.000%

    No Known Activations