© 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. 51796
    Prev
    Next
    INDEX
    Explanations

    quantization, speed, quality, agents, search

    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
     amounted
    0.43
     なかっ
    0.42
    ាស់
    0.42
    EVENTS
    0.40
    }$')
    0.40
    ෙන්
    0.39
    であった
    0.39
     benefitted
    0.39
     өз
    0.39
    的事情
    0.38
    POSITIVE LOGITS
     și
    0.45
     defenseman
    0.45
     wide
    0.44
    ریض
    0.43
     Wide
    0.43
    Par
    0.42
    𝓵
    0.42
     பர
    0.41
    Multi
    0.40
     multicolor
    0.40
    Activations Density 0.002%

    No Known Activations