© 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. 97546
    Prev
    Next
    INDEX
    Explanations

    contract conclusion or contract performance

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

    sequences like "once required" or "once felt"

    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
     compartido
    0.52
    发行
    0.49
     quedan
    0.49
     ş
    0.48
     răm
    0.47
    和
    0.47
    뭍
    0.46
     chiaro
    0.45
     pubblic
    0.45
     littérature
    0.45
    POSITIVE LOGITS
    peasants
    0.49
     भवि
    0.43
     Danke
    0.42
    توا
    0.42
     مس
    0.42
    anoj
    0.42
    춰
    0.41
    ukun
    0.41
     Chakrab
    0.40
     villagers
    0.40
    Activations Density 0.000%

    No Known Activations