© 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. 6301
    Prev
    Next
    INDEX
    Explanations

    in followed by other words

    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
    K
    0.65
    '')
    0.59
    ]-
    0.58
    M
    0.57
    hane
    0.57
    ]:
    0.55
    S
    0.55
    D
    0.55
    -:
    0.53
    )：
    0.52
    POSITIVE LOGITS
    هم
    0.83
     vào
    0.67
    のは
    0.66
    ના
    0.63
    ना
    0.63
    να
    0.59
     a
    0.58
     сюда
    0.57
    ни
    0.55
    នូវ
    0.54
    Activations Density 0.039%

    No Known Activations