© 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. 242654
    Prev
    Next
    INDEX
    Explanations

    valuations, timeline

    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
    泳
    0.58
    nice
    0.57
    yin
    0.55
    finished
    0.52
    sunday
    0.52
    ка
    0.52
    gür
    0.51
    swim
    0.50
    다
    0.50
    first
    0.49
    POSITIVE LOGITS
     علاج
    0.52
     木製
    0.51
     obstru
    0.49
     무
    0.49
     Druck
    0.49
     בפ
    0.48
     דר
    0.47
     マルチ
    0.47
     durchaus
    0.46
     litt
    0.46
    Activations Density 0.001%

    No Known Activations