© 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. 219261
    Prev
    Next
    INDEX
    Explanations

    working group reported

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

    size of, EU, distance, gone a

    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
    屐
    0.62
    damping
    0.58
    classroom
    0.54
    倫
    0.50
     現在
    0.49
    地点
    0.48
    流
    0.47
    伦
    0.47
    場所
    0.46
     Palest
    0.46
    POSITIVE LOGITS
    {
    0.52
     shocked
    0.49
    pone
    0.46
     avea
    0.46
     flashbacks
    0.45
     avait
    0.44
    zat
    0.43
     estaban
    0.42
     were
    0.42
     was
    0.42
    Activations Density 0.001%

    No Known Activations