© 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. 31-GEMMASCOPE-2-RES-262K
    7. 56623
    Prev
    Next
    INDEX
    Explanations

    used even

    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_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
    త
    0.42
     وړیا
    0.41
     얼마
    0.41
    aterData
    0.41
     обнов
    0.40
    畈
    0.40
    သေး
    0.40
    파일명
    0.40
    確か
    0.40
    য়
    0.40
    POSITIVE LOGITS
     cognit
    0.42
     beliefs
    0.39
     policym
    0.39
     suppressing
    0.39
    FFER
    0.39
     گے۔
    0.39
        
    0.38
     kuin
    0.38
    strategic
    0.38
    <td>
    0.38
    Activations Density 0.013%

    No Known Activations