© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 41244
    Prev
    Next
    INDEX
    Explanations

    xml declaration encoding

    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
     and
    1.05
    1.05
     l
    0.92
     covalent
    0.92
     t
    0.91
    ט
    0.88
     tachycardia
    0.87
     solubility
    0.86
     plasmid
    0.85
     trellis
    0.85
    POSITIVE LOGITS
    at
    1.25
    is
    1.09
    де
    1.05
    n
    1.05
    as
    1.05
    ok
    1.01
     émissions
    0.94
    nél
    0.92
    ong
    0.91
    ier
    0.90
    Activations Density 0.000%

    No Known Activations