© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31021
    Prev
    Next
    INDEX
    Explanations

    export default

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aquaculture
    0.55
    бата
    0.54
     particulate
    0.53
     carbide
    0.53
     carbure
    0.53
    ])$
    0.52
     antif
    0.52
    อาหาร
    0.52
     refractory
    0.51
     Haf
    0.51
    POSITIVE LOGITS
    u
    0.52
    House
    0.51
    plots
    0.46
    房子
    0.46
    洲
    0.46
    <0x8A>
    0.46
    טל
    0.46
    <0xA0>
    0.45
    তা
    0.45
    рили
    0.45
    Activations Density 0.005%

    No Known Activations