© 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. 16-GEMMASCOPE-2-RES-262K
    7. 19596
    Prev
    Next
    INDEX
    Explanations

    pillars of

    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_16_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
    g
    0.80
    ó
    0.78
    z
    0.73
    d
    0.73
    я
    0.71
    )
    0.69
    SIZE
    0.68
    å
    0.68
    Ꮽ
    0.67
    u
    0.66
    POSITIVE LOGITS
     pillars
    1.06
    pillars
    0.99
     pillar
    0.91
     bastion
    0.84
    amiento
    0.82
     underpin
    0.80
    onde
    0.79
    urin
    0.79
     Pillars
    0.79
     aromatic
    0.77
    Activations Density 0.023%

    No Known Activations