© 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-262K
    7. 91424
    Prev
    Next
    INDEX
    Explanations

    explaining qualities or states that often precede descriptions

    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
     самих
    0.48
    𝘁
    0.46
    ȩ
    0.45
     рекомендации
    0.44
    orten
    0.43
     કુ
    0.43
     sogenannten
    0.42
    🤛
    0.42
     αντί
    0.41
     sogen
    0.41
    POSITIVE LOGITS
     because
    0.58
     porque
    0.54
     undoubtedly
    0.53
     but
    0.50
    Because
    0.50
    是一個
    0.47
     inherently
    0.47
    因为它
    0.47
     BECAUSE
    0.46
     потому
    0.46
    Activations Density 0.054%

    No Known Activations