© 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-65K
    7. 40922
    Prev
    Next
    INDEX
    Explanations

    unused items or conditions

    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
     injust
    0.37
    짰
    0.37
    Ⲉ
    0.37
    ypi
    0.36
    ButtonClick
    0.36
    ccn
    0.35
    觀眾
    0.35
     التمث
    0.35
    ccncc
    0.35
    עד
    0.35
    POSITIVE LOGITS
     intact
    0.46
     undamaged
    0.44
    fresh
    0.39
    andal
    0.38
    iento
    0.38
     कंडिशनर
    0.38
    干净
    0.38
    糟
    0.38
     soiled
    0.38
     выпа
    0.38
    Activations Density 0.011%

    No Known Activations