© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 80586
    Prev
    Next
    INDEX
    Explanations

    past thoughts and states

    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_53_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
    Zw
    0.41
    此前
    0.39
    √
    0.37
    参照
    0.36
    ljenje
    0.35
    وزر
    0.35
    ÁS
    0.35
     $_{
    0.34
    °)
    0.33
     семье
    0.33
    POSITIVE LOGITS
     hoping
    0.79
     wondering
    0.76
     thinking
    0.65
     trying
    0.63
     told
    0.61
     expecting
    0.56
     tempted
    0.54
     Hoping
    0.54
     wishing
    0.53
     worth
    0.52
    Activations Density 0.005%

    No Known Activations