© 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. 20868
    Prev
    Next
    INDEX
    Explanations

    if you

    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
    étr
    0.51
     IPCC
    0.50
     objectifs
    0.49
    >≥</
    0.49
    Objectives
    0.48
     of
    0.47
    這
    0.46
    㷅
    0.46
    Así
    0.45
    捃
    0.45
    POSITIVE LOGITS
    zv
    0.44
     bpm
    0.43
    тами
    0.42
    RIN
    0.41
     ngunit
    0.40
    sna
    0.40
    but
    0.39
     derivable
    0.39
    独自
    0.39
    uah
    0.39
    Activations Density 0.012%

    No Known Activations