© 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. 133662
    Prev
    Next
    INDEX
    Explanations

    assessments and data

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

    signals for data processing

    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
    rou
    0.49
    s
    0.45
    cou
    0.45
    草
    0.44
    ter
    0.44
    me
    0.44
    that
    0.42
    Shi
    0.42
    co
    0.42
    were
    0.42
    POSITIVE LOGITS
     datasets
    0.57
    考試
    0.54
    یوں
    0.52
     म्यु
    0.52
    ༔
    0.50
     dungeons
    0.49
     pemeriksaan
    0.49
    assess
    0.49
     walaupun
    0.49
     ڈیٹا
    0.48
    Activations Density 0.000%

    No Known Activations