© 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. 27124
    Prev
    Next
    INDEX
    Explanations

    collapse 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
    _
    0.98
    กับ
    0.91
    จะ
    0.82
     जिसका
    0.82
    ands
    0.80
     труб
    0.77
     рост
    0.74
    iving
    0.74
    .(\
    0.73
    ically
    0.73
    POSITIVE LOGITS
    at
    1.16
    et
    1.09
    u
    1.03
    el
    1.02
     Collapse
    1.00
    am
    0.98
    ే
    0.98
    ac
    0.88
    ap
    0.86
    is
    0.84
    Activations Density 0.004%

    No Known Activations