© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 218
    Prev
    Next
    INDEX
    Explanations

    we or i

    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_16k_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
    ↵
    0.18
     undamaged
    0.17
     thriving
    0.16
     fading
    0.16
     گئی۔
    0.16
     harrowing
    0.16
     furnishing
    0.16
    dynamic
    0.15
     className
    0.15
     formidable
    0.15
    POSITIVE LOGITS
    utiliser
    0.22
    ات
    0.19
    ←
    0.19
    ks
    0.18
     will
    0.18
     incluye
    0.18
    蕤
    0.17
    сера
    0.17
    ках
    0.17
    pls
    0.17
    Activations Density 0.459%

    No Known Activations