© 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-65K
    7. 30200
    Prev
    Next
    INDEX
    Explanations

    building wealth

    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
    Instant
    0.55
    instant
    0.54
    Cer
    0.53
    acted
    0.52
    J
    0.52
    Baseline
    0.51
    Social
    0.51
    LLO
    0.50
     Conta
    0.50
    FIED
    0.49
    POSITIVE LOGITS
     verursacht
    0.44
    ний
    0.43
    -
    0.43
     ebenfalls
    0.41
     normalerweise
    0.41
     sowohl
    0.40
    isi
    0.40
    碑
    0.40
     neben
    0.39
     geboren
    0.39
    Activations Density 0.005%

    No Known Activations