© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 29289
    Prev
    Next
    INDEX
    Explanations

    adsorption and ion exchange materials

    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_40_width_262k_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
    唥
    0.42
    辏
    0.40
     تشدد
    0.39
     пропа
    0.39
    推进
    0.39
     праз
    0.39
     celebration
    0.38
    槙
    0.38
    Aile
    0.38
     नकार
    0.38
    POSITIVE LOGITS
     adsorbent
    1.73
     adsor
    1.69
     adsorption
    1.66
     adsorb
    1.65
     absorbent
    1.64
     absorb
    1.52
     absor
    1.46
     absorbing
    1.46
    absor
    1.37
     absorption
    1.35
    Activations Density 0.016%

    No Known Activations