© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129167
    Prev
    Next
    INDEX
    Explanations

    information for further action

    np_acts-logits-general · gemini-2.5-flash-lite

    steps, patient, tracking, kayaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IdleSync
    0.47
    、$
    0.46
    மக்கு
    0.46
    策
    0.45
    CTOGRAM
    0.44
    អ្នក
    0.43
     निश्चित
    0.43
     متعلقه
    0.42
    យើង
    0.42
    礦
    0.42
    POSITIVE LOGITS
    hang
    0.51
     open
    0.50
    behaved
    0.49
    <0xE6>
    0.49
     comport
    0.49
     staging
    0.48
    грани
    0.47
     s
    0.46
    banding
    0.46
     ROH
    0.46
    Activations Density 0.000%

    No Known Activations