© 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. 53654
    Prev
    Next
    INDEX
    Explanations

    too much / too little

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

    explaining concepts

    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
    …"
    0.46
     aufgenommen
    0.46
     Oldham
    0.46
     Kindern
    0.46
    ]+")
    0.45
     начале
    0.45
     приорите
    0.45
    LENGTH
    0.44
    䔀
    0.43
     процеду
    0.42
    POSITIVE LOGITS
     would
    0.55
     republics
    0.51
     despite
    0.50
     loses
    0.49
     substitute
    0.49
     divs
    0.49
     screenshot
    0.49
     snapshot
    0.49
     snapshots
    0.49
     mimics
    0.49
    Activations Density 0.000%

    No Known Activations