© 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. 136107
    Prev
    Next
    INDEX
    Explanations

    string formation, talk prohibition

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

    hosting, value, building, name, UI

    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
    iritual
    0.49
    琐
    0.49
     constantes
    0.46
    徊
    0.46
     ह
    0.45
     जबकि
    0.44
    ស្រាយ
    0.43
    eti
    0.43
     generales
    0.42
    }}<
    0.42
    POSITIVE LOGITS
     TCM
    0.52
    동산
    0.50
    я
    0.47
     average
    0.46
     scrapped
    0.45
     environmentally
    0.44
     sạch
    0.44
     axles
    0.44
     Macs
    0.44
    旁邊
    0.44
    Activations Density 0.000%

    No Known Activations